hexagon: enable offloading to Hexagon on Windows on Snapdragon (#19150)

* hexagon: updates to enable offloading to HTP on WoS

* Update windows.md

* Update windows.md

* hexagon: enable -O3 optimizations

* hexagon: move all _WINDOWS conditional compilation to _WIN32

* hexagon: updates to enable offloading to HTP on WoS

* hexagon: use run-time vs load-time dynamic linking for cdsp driver interface

* refactor htp-drv

* hexagon: add run-bench.ps1 script

* hexagon: htdrv refactor

* hexagon: unify Android and Windows build readmes

* hexagon: update README.md

* hexagon: refactor htpdrv

* hexagon: drv refactor

* hexagon: more drv refactor

* hexagon: fixes for android builds

* hexagon: factor out dl into ggml-backend-dl

* hexagon: add run-tool.ps1 script

* hexagon: merge htp-utils in htp-drv and remove unused code

* wos: no need for getopt_custom.h

* wos: add missing CR in htpdrv

* hexagon: ndev enforecement applies only to the Android devices

* hexagon: add support for generating and signing .cat file

* hexagon: add .inf file

* hexagon: working auto-signing and improved windows builds

* hexagon: futher improve skel build

* hexagon: add rough WoS guide

* hexagon: updated windows guide

* hexagon: improve cmake handling of certs and logging

* hexagon: improve windows setup/build doc

* hexagon: more windows readme updates

* hexagon: windows readme updates

* hexagon: windows readme updates

* hexagon: windows readme updates

* hexagon: windows readme updates

* Update windows.md

* Update windows.md

* snapdragon: rename docs/backend/hexagon to docs/backends/snapdragon

Also added a power shell script to simplify build env setup.

* hexagon: remove trailing whitespace and move cmake requirement to user-presets

* hexagon: fix CMakeUserPresets path in workflow yaml

* hexagon: introduce local version of libdl.h

* hexagon: fix src1 reuse logic

gpt-oss needs a bigger lookahead window.
The check for src[1] itself being quantized was wrong.

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>

.github/workflows/build.yml

@@ -1371,7 +1371,7 @@ jobs:
         id: update_presets
         if: ${{ matrix.build == 'arm64-snapdragon' }}
         run: |
-          cp docs/backend/hexagon/CMakeUserPresets.json .
+          cp docs/backend/snapdragon/CMakeUserPresets.json .
 
       - name: Build
         id: ndk_build

common/chat.cpp

@@ -2571,20 +2571,165 @@ static common_chat_params common_chat_params_init_granite(const common_chat_temp
 static common_chat_params common_chat_params_init_solar_open(const common_chat_template & tmpl, const struct templates_params & inputs) {
     common_chat_params data;
 
-    // TODO: Reasoning effort
-    json additional_context = {};
+    // Copy `reasoning_content` to `reasoning`
+    auto adjusted_messages = json::array();
+    for (const auto & msg : inputs.messages) {
+        if (msg.contains("reasoning_content") && msg.at("reasoning_content").is_string()) {
+            auto adjusted_message = msg;
+            adjusted_message["reasoning"] = msg.at("reasoning_content");
+            adjusted_message.erase("reasoning_content");
+            adjusted_messages.push_back(adjusted_message);
+        } else {
+            adjusted_messages.push_back(msg);
+        }
+    }
 
-    data.prompt = apply(tmpl, inputs, std::nullopt, std::nullopt, additional_context);
-    data.format = COMMON_CHAT_FORMAT_SOLAR_OPEN;
+    auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
+    auto include_grammar = true;
 
+    auto prompt = apply(tmpl, inputs, /* messages_override= */ adjusted_messages);
+
+    // Check if we need to replace the flush token with end token during inference and without generation prompt.
+    if (inputs.is_inference && !inputs.add_generation_prompt) {
+        static constexpr std::string_view return_token = "<|flush|>";
+        static constexpr std::string_view end_token    = "<|end|>";
+        if (size_t pos = prompt.rfind(return_token); pos != std::string::npos) {
+            prompt.replace(pos, return_token.length(), end_token);
+        }
+    }
+
+    data.prompt = prompt;
+    data.format = COMMON_CHAT_FORMAT_PEG_NATIVE;
     data.preserved_tokens = {
         "<|think|>",
         "<|content|>",
         "<|begin|>",
         "<|end|>",
+        "<|tool_calls|>",
+        "<|tool_call:begin|>",
+        "<|tool_call:end|>",
+        "<|tool_call:name|>",
+        "<|tool_call:args|>",
     };
 
-    // TODO: Tool calling
+    auto parser = build_chat_peg_native_parser([&](common_chat_peg_native_builder & p) {
+        auto lit_think = p.atomic(p.literal("<|think|>"));
+        auto lit_assistant_begin = p.atomic(p.literal("<|begin|>assistant"));
+        auto lit_content = p.atomic(p.literal("<|content|>"));
+        auto lit_end = p.atomic(p.literal("<|end|>"));
+        auto parser_until_end = p.until("<|end|>");
+
+        // reasoning <- "<|think|>" (!"<|end|>" .)*
+        auto parser_reasoning = p.rule("reasoning", lit_think + p.reasoning(parser_until_end));
+
+        // content <- "<|content|>" (!"<|end|>" .)*
+        auto parser_content = p.rule("content", lit_content + p.content(parser_until_end));
+
+        // wrap_choice(items) <- item-choice wrapped*
+        // item-choice        <- items[0] / ... / items[n]
+        // wrapped            <- "<|end|><|begin|>assistant" item-choice
+        auto wrap_choice = [&](const std::vector<common_peg_parser> & items) {
+            auto choice = p.choice(items);
+            return choice + p.zero_or_more(lit_end + lit_assistant_begin + choice);
+        };
+
+        // wrap_seq(items) <- item[0] "<|end|><|begin|>assistant" item[1] ...
+        auto wrap_seq = [&](const std::vector<common_peg_parser> & items) {
+            auto seq = p.sequence();
+            for (auto i = 0u; i < items.size(); i++) {
+                if (i == 0) {
+                    seq += items[i];
+                    continue;
+                }
+                seq += lit_end + lit_assistant_begin + items[i];
+            }
+            return seq;
+        };
+
+        // Response format parser
+        if (inputs.json_schema.is_object() && !inputs.json_schema.empty()) {
+            auto parser_response_format = lit_content + p.content(p.schema(p.json(), "response-format", inputs.json_schema));
+            return p.choice({
+                wrap_seq({parser_reasoning, parser_response_format}),
+                wrap_seq({parser_response_format})
+            });
+        }
+
+        auto lit_tool_call_begin = p.literal("<|tool_call:begin|>");
+        auto lit_tool_call_name = p.literal("<|tool_call:name|>");
+        auto lit_tool_call_args = p.literal("<|tool_call:args|>");
+        auto lit_tool_call_end = p.literal("<|tool_call:end|>");
+
+        // Tool call parser
+        if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE) {
+            auto parser_tool_call = p.choice();
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto & function = tool.at("function");
+                std::string name = function.at("name");
+                const auto & schema = function.at("parameters");
+
+                // tool(name, schema) <- name "<|tool_call:args|>" schema
+                parser_tool_call |= p.rule("tool-" + name,
+                    p.atomic(p.tool_name(p.literal(name)) + lit_tool_call_args)
+                    + p.tool_args(p.schema(p.json(), "tool-" + name + "-schema", schema)));
+            });
+
+            auto min_calls = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED ? 1 : 0;
+            auto max_calls = inputs.parallel_tool_calls ? -1 : 1;
+
+            // tool-calls  <- "<|tool_calls|>" tool-call+
+            // tool-call   <- "<|tool_call:begin|> call-id "<|tool_call:name|>" &([^<]+ "<|tool_call:args|>") tool-choice "<|tool_call:end|>"
+            // call-id     <- [a-zA-Z0-9_-]+
+            // tool-choice <- tool(t[0].name, t[0].schema) / ... / tool(t[n].name, t[n].schema)
+            auto parser_tool_calls = p.trigger_rule("tool-calls",
+                p.atomic(p.literal("<|tool_calls|>"))
+                + p.repeat(
+                    p.tool_open(
+                        lit_tool_call_begin
+                        + p.tool_id(p.chars("[a-zA-Z0-9_-]", 1, -1))
+                        + lit_tool_call_name
+                        + p.peek(p.chars("[^<]", 1, -1) + lit_tool_call_args))
+                    + parser_tool_call
+                    + p.tool_close(lit_tool_call_end),
+                /* min = */ 1,
+                /* max = */ max_calls));
+
+            if (min_calls == 1) {
+                // If required, then try any combination of the reasoning, content, and tool call
+                return p.choice({
+                    wrap_seq({parser_reasoning, parser_content, parser_tool_calls}),
+                    wrap_seq({parser_reasoning, parser_tool_calls}),
+                    wrap_seq({parser_content, parser_tool_calls}),
+                    wrap_seq({parser_tool_calls})
+                });
+            }
+
+            return wrap_choice({parser_reasoning, parser_content, parser_tool_calls});
+        }
+
+        // Content only parser
+        include_grammar = false;
+        return wrap_choice({parser_reasoning, parser_content});
+    });
+
+    data.parser = parser.save();
+
+    if (include_grammar) {
+        data.grammar_lazy = has_tools && inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_AUTO;
+
+        data.grammar = build_grammar([&](const common_grammar_builder & builder) {
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto & function = tool.at("function");
+                auto schema = function.at("parameters");
+                builder.resolve_refs(schema);
+            });
+            parser.build_grammar(builder, data.grammar_lazy);
+        });
+
+        data.grammar_triggers = {
+            {COMMON_GRAMMAR_TRIGGER_TYPE_WORD, "<|tool_calls|>"}
+        };
+    }
 
     return data;
 }
@@ -3041,6 +3186,13 @@ static common_chat_params common_chat_templates_apply_jinja(
         return common_chat_params_init_apriel_1_5(tmpl, params);
     }
 
+    // Solar Open
+    if (src.find("<|tool_response:begin|>") != std::string::npos &&
+        src.find("<|tool_response:name|>") != std::string::npos &&
+        src.find("<|tool_response:result|>") != std::string::npos) {
+        return common_chat_params_init_solar_open(tmpl, params);
+    }
+
     // Use generic handler when mixing tools + JSON schema.
     // TODO: support that mix in handlers below.
     if ((params.tools.is_array() && params.json_schema.is_object())) {

docs/backend/snapdragon/CMakeUserPresets.json

@@ -1,5 +1,10 @@
 {
-  "version": 4,
+  "version": 5,
+  "cmakeMinimumRequired": {
+      "major": 3,
+      "minor": 28,
+      "patch": 0
+  },
   "configurePresets": [
     {
         "name": "arm64-android-snapdragon",
@@ -16,7 +21,9 @@
             "CMAKE_CXX_FLAGS_RELEASE":        "-O3 -DNDEBUG",
             "CMAKE_C_FLAGS_RELWITHDEBINFO":   "-O3 -DNDEBUG -g",
             "CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
-            "HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}",
+            "CMAKE_PREFIX_PATH":  "$env{OPENCL_SDK_ROOT}",
+            "HEXAGON_SDK_ROOT":   "$env{HEXAGON_SDK_ROOT}",
+            "HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}",
             "PREBUILT_LIB_DIR": "android_aarch64",
             "GGML_OPENMP":      "OFF",
             "GGML_LLAMAFILE":   "OFF",
@@ -31,7 +38,15 @@
         "name": "arm64-windows-snapdragon",
         "inherits": [ "base", "arm64-windows-llvm" ],
         "cacheVariables": {
-            "HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}",
+            "CMAKE_C_FLAGS":   "-march=armv8.7a+fp16 -fvectorize -ffp-model=fast -flto -D_GNU_SOURCE",
+            "CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16 -fvectorize -ffp-model=fast -flto -D_GNU_SOURCE",
+            "CMAKE_C_FLAGS_RELEASE":          "-O3 -DNDEBUG",
+            "CMAKE_CXX_FLAGS_RELEASE":        "-O3 -DNDEBUG",
+            "CMAKE_C_FLAGS_RELWITHDEBINFO":   "-O3 -DNDEBUG -g",
+            "CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
+            "CMAKE_PREFIX_PATH":  "$env{OPENCL_SDK_ROOT}",
+            "HEXAGON_SDK_ROOT":   "$env{HEXAGON_SDK_ROOT}",
+            "HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}",
             "PREBUILT_LIB_DIR": "windows_aarch64",
             "GGML_OPENMP":      "OFF",
             "GGML_LLAMAFILE":   "OFF",

docs/backend/snapdragon/README.md

@@ -1,6 +1,8 @@
-# Snapdragon-based Android devices
+# Snapdragon-based devices
 
-## How to Build
+## Setup
+
+### Android
 
 The easiest way to build llama.cpp for a Snapdragon-based Android device is using the toolchain Docker image (see github.com/snapdragon-toolchain).
 This image includes Android NDK, OpenCL SDK, Hexagon SDK, CMake, etc.
@@ -12,7 +14,24 @@ This method works on Linux, macOS, and Windows. macOS and Windows users should i
 [d]/> cd /workspace
 ```
 
-The rest of the Android build process assumes that you're running inside the toolchain container.
+Note: The rest of the **Android** build process assumes that you're running inside the toolchain container.
+
+### Windows On Snapdragon
+
+Native Windows 11 arm64 builds has the following tools dependencies:
+- MS Visual Studio 2026 (Community Edition or Pro)
+  - MSVC arm64 standard and runtime libraries
+  - UCRT and Driver Kit
+- LLVM core libraries and Clang compiler (winget)
+- CMake, Git, Python (winget)
+- Hexagon SDK Community Edition 6.4 or later (see windows.md)
+- OpenCL SDK 2.3 or later (see windows.md)
+
+Note: The rest of the **Windows** build process assumes that you're running natively in Powershell.
+Adapt below build commands accordingly.
+
+## How to Build
+
 Let's build llama.cpp with CPU, OpenCL, and Hexagon backends via CMake presets:
 
 ```
@@ -49,24 +68,26 @@ Preset CMake variables:
 To generate an installable "package" simply use cmake --install:
 
 ```
-[d]/workspace> cmake --install build-snapdragon --prefix pkg-adb/llama.cpp
+[d]/workspace> cmake --install build-snapdragon --prefix pkg-snapdragon/llama.cpp
 -- Install configuration: "Release"
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-cpu.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-opencl.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-hexagon.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-htp-v73.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-htp-v75.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-htp-v79.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml-htp-v81.so
--- Installing: /workspace/pkg-adb/llama.cpp/lib/libggml.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-cpu.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-opencl.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-hexagon.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-htp-v73.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-htp-v75.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-htp-v79.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml-htp-v81.so
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/lib/libggml.so
 ...
--- Installing: /workspace/pkg-adb/llama.cpp/bin/llama-bench
--- Installing: /workspace/pkg-adb/llama.cpp/bin/llama-cli
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/bin/llama-bench
+-- Installing: /workspace/pkg-snapdragon/llama.cpp/bin/llama-cli
 ...
 ```
 
 ## How to Install
 
+### Android
+
 For this step, your device needs to be configured for on-device development.
 Please see https://developer.android.com/studio/debug/dev-options for details.
 
@@ -74,10 +95,10 @@ Once ADB is enabled, use `adb push` to install `pkg-snapdragon` on the device.
 **Note that the toolchain Docker image doesn't have ADB and doesn't set up the ADB bridge. Please use native ADB on the host.**
 
 ```
-~/src/llama.cpp$ adb push pkg-adb/llama.cpp /data/local/tmp/
-pkg-adb/llama.cpp/bin/: 67 files pushed, 0 skipped. 190.2 MB/s (919095042 bytes in 4.607s)
-pkg-adb/llama.cpp/include/: 19 files pushed, 0 skipped. 20.5 MB/s (255173 bytes in 0.012s)
-pkg-adb/llama.cpp/lib/: 16 files pushed, 0 skipped. 144.4 MB/s (43801382 bytes in 0.289s)
+~/src/llama.cpp$ adb push pkg-snapdragon/llama.cpp /data/local/tmp/
+pkg-snapdragon/llama.cpp/bin/: 67 files pushed, 0 skipped. 190.2 MB/s (919095042 bytes in 4.607s)
+pkg-snapdragon/llama.cpp/include/: 19 files pushed, 0 skipped. 20.5 MB/s (255173 bytes in 0.012s)
+pkg-snapdragon/llama.cpp/lib/: 16 files pushed, 0 skipped. 144.4 MB/s (43801382 bytes in 0.289s)
 102 files pushed, 0 skipped. 186.9 MB/s (963151597 bytes in 4.914s)
 ```
 
@@ -92,6 +113,11 @@ At this point, you should also install some models:
 Llama-3.2-1B-Instruct-Q4_0.gguf: 1 file pushed, 0 skipped. 38.3 MB/s (773025920 bytes in 19.250s)
 ```
 
+### Windows
+
+All artifacts are already installed in the `pkg-snapdragon` folder.
+To run, adapt below instructions to use Powershell scrits in `scripts/snapdragon/windows`.
+
 ## How to Run
 
 The easiest way to run llama.cpp cli tools is using provided wrapper scripts that properly set up all required environment variables.

docs/backend/snapdragon/windows.md

@@ -0,0 +1,161 @@
+## Overview
+
+The document covers procedures for installing the latest GPU and NPU drivers, and OpenCL and Hexagon SDKs.
+
+
+In order to use Hexagon NPU on Snapdragon Windows devices the underlying HTP Ops libraries (e.g libggml-htp-v73.so)
+must be included in the .cat file digitally signed with a trusted certificate.
+
+This document covers details on how to generate personal certificate files (.pfx) and how to configure the system
+to allow for test signatures (aka test-signing).
+
+## Install the latest Adreno OpenCL SDK
+
+Either use the trimmed down version (optimized for CI) from
+
+    https://github.com/snapdragon-toolchain/opencl-sdk/releases/download/v2.3.2/adreno-opencl-sdk-v2.3.2-arm64-wos.tar.xz
+
+Or download the complete official version from
+
+    https://softwarecenter.qualcomm.com/catalog/item/Adreno_OpenCL_SDK?version=2.3.2
+
+Unzip/untar the archive into
+```
+c:\Qualcomm\OpenCL_SDK\2.3.2
+```
+
+## Install the latest Hexagon SDK Community Edition
+
+Either use the trimmed down version (optimized for CI) from
+
+    https://github.com/snapdragon-toolchain/hexagon-sdk/releases/download/v6.4.0.2/hexagon-sdk-v6.4.0.2-arm64-wos.tar.xz
+
+Or download the complete official version from
+
+    https://softwarecenter.qualcomm.com/catalog/item/Hexagon_SDK?version=6.4.0.2
+
+Unzip/untar the archive into
+```
+c:\Qualcomm\Hexagon_SDK\6.4.0.2
+```
+
+## Install the latest Adreno GPU driver
+
+Download the driver from
+
+    https://softwarecenter.qualcomm.com/catalog/item/Windows_Graphics_Driver
+
+After the automated installation and reboot please make sure that the GPU device shows up in the `Device Manager` (under 'Display Adapters`)
+
+## Install the latest Qualcomm NPU driver
+
+Download the driver from
+
+    https://softwarecenter.qualcomm.com/catalog/item/Qualcomm_HND
+
+After the automated installation and reboot please make sure that the Hexagon NPU device shows up in the `Device Manager` (under `Neural Processors`).
+
+If the device is not available you can try installing all components (`qcnspmcdm8380`, `qcnspmcdm8380_ext`) manually.
+The components are extracted into
+```
+c:\QCDrivers\qcnspmcdm...
+```
+
+## Enable NPU driver test signatures
+
+Please note that the following steps are required only for the Hexagon NPU.
+Adreno GPU backend does not require test signatures.
+
+### Enable testsigning
+
+Use `bcdedit` to enable test-signing
+```
+> bcdedit /set TESTSIGNING ON
+```
+(Secure Boot may need to be disabled for this to work)
+
+Make sure test-signing is enabled after reboot
+```
+> bcdedit /enum
+...
+testsigning             Yes
+...
+```
+For additional details see Microsoft guide at
+
+   https://learn.microsoft.com/en-us/windows-hardware/drivers/install/the-testsigning-boot-configuration-option
+
+### Create personal certificate
+
+The tools required for this procedure are available as part of Windows SDK and Windows Driver Kit which should be
+installed as part of the MS Visual Studio.
+They are typically located at
+```
+c:\Program Files (x86)\Windows Kits\10\bin\10.0.26100.0
+```
+(replace 10.0.26100.0 with correct version).
+
+To create personal self-signed certificate run the following commands (either from cmd or power-shell):
+```
+> cd c:\Users\MyUser
+> mkdir Certs
+> cd Certs
+> makecert -r -pe -ss PrivateCertStore -n CN=GGML.HTP.v1 -eku 1.3.6.1.5.5.7.3.3 -sv ggml-htp-v1.pvk ggml-htp-v1.cer
+> pvk2pfx.exe -pvk ggml-htp-v1.pvk -spc ggml-htp-v1.cer -pfx ggml-htp-v1.pfx
+```
+(replace `MyUser` with your username).
+
+Add this certificate to `Trusted Root Certification Authorities` and `Trusted Publishers` stores.
+This can be done using `certlm` Certificate Manager tool.
+Right click on the certificate store, select `All Tasks -> Import` and follow the prompts to import the certificate from the
+PFX file you created above.
+
+For additional details see Microsoft guide at
+
+    https://learn.microsoft.com/en-us/windows-hardware/drivers/install/introduction-to-test-signing
+
+Make sure to save the PFX file, you will need it for the build procedures.
+Please note that the same certificate can be used for signing any number of builds.
+
+## Build Hexagon backend with signed HTP ops libraries
+
+The overall Hexagon backend build procedure for Windows on Snapdragon is the same as for other platforms.
+However, additional settings are required for generating and signing HTP Ops libraries.
+```
+> $env:OPENCL_SDK_ROOT="C:\Qualcomm\OpenCL_SDK\2.3.2"
+> $env:HEXAGON_SDK_ROOT="C:\Qualcomm\Hexagon_SDK\6.4.0.2"
+> $env:HEXAGON_TOOLS_ROOT="C:\Qualcomm\Hexagon_SDK\6.4.0.2\tools\HEXAGON_Tools\19.0.04"
+> $env:HEXAGON_HTP_CERT="c:\Users\MyUsers\Certs\ggml-htp-v1.pfx"
+> $env:WINDOWS_SDK_BIN="C:\Program Files (x86)\Windows Kits\10\bin\10.0.26100.0\arm64"
+
+> cmake --preset arm64-windows-snapdragon -B build-wos
+...
+> cmake --install build-wos --prefix pkg-snapdragon
+```
+
+Once the build is complete HTP ops libraries will be installed like this
+```
+> dir pkg-snapdragon/lib
+...
+-a----         1/22/2026   6:01 PM         187656 libggml-htp-v73.so
+-a----         1/22/2026   6:01 PM         191752 libggml-htp-v75.so
+-a----         1/22/2026   6:01 PM         187656 libggml-htp-v79.so
+-a----         1/22/2026   6:01 PM         187656 libggml-htp-v81.so
+-a----         1/22/2026   6:01 PM           4139 libggml-htp.cat
+```
+
+The .cat file, the signature and proper certicate installation can be verified with
+
+```
+> signtool.exe verify /v /pa .\pkg-snapdragon\lib\libggml-htp.cat
+Verifying: .\pkg-snapdragon\lib\libggml-htp.cat
+
+Signature Index: 0 (Primary Signature)
+Hash of file (sha256): 9820C664DA59D5EAE31DBB664127FCDAEF59CDC31502496BC567544EC2F401CF
+
+Signing Certificate Chain:
+        Issued to: GGML.HTP.v1
+...
+Successfully verified: .\pkg-snapdragon\lib\libggml-htp.cat
+...
+```

ggml/src/CMakeLists.txt

@@ -222,6 +222,7 @@ if (GGML_SCHED_NO_REALLOC)
 endif()
 
 add_library(ggml
+            ggml-backend-dl.cpp
             ggml-backend-reg.cpp)
 add_library(ggml::ggml ALIAS ggml)
 

ggml/src/ggml-backend-dl.cpp

@@ -0,0 +1,48 @@
+#include "ggml-backend-dl.h"
+
+#ifdef _WIN32
+
+dl_handle * dl_load_library(const fs::path & path) {
+    // suppress error dialogs for missing DLLs
+    DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+    SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+    HMODULE handle = LoadLibraryW(path.wstring().c_str());
+
+    SetErrorMode(old_mode);
+
+    return handle;
+}
+
+void * dl_get_sym(dl_handle * handle, const char * name) {
+    DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+    SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+    void * p = (void *) GetProcAddress(handle, name);
+
+    SetErrorMode(old_mode);
+
+    return p;
+}
+
+const char * dl_error() {
+    return "";
+}
+
+#else
+
+dl_handle * dl_load_library(const fs::path & path) {
+    dl_handle * handle = dlopen(path.string().c_str(), RTLD_NOW | RTLD_LOCAL);
+    return handle;
+}
+
+void * dl_get_sym(dl_handle * handle, const char * name) {
+    return dlsym(handle, name);
+}
+
+const char * dl_error() {
+    const char *rslt = dlerror();
+    return rslt != nullptr ? rslt : "";
+}
+
+#endif

ggml/src/ggml-backend-dl.h

@@ -0,0 +1,45 @@
+#pragma once
+
+#ifdef _WIN32
+#   define WIN32_LEAN_AND_MEAN
+#   ifndef NOMINMAX
+#       define NOMINMAX
+#   endif
+#   include <windows.h>
+#   include <winevt.h>
+#else
+#    include <dlfcn.h>
+#    include <unistd.h>
+#endif
+#include <filesystem>
+
+namespace fs = std::filesystem;
+
+#ifdef _WIN32
+
+using dl_handle = std::remove_pointer_t<HMODULE>;
+
+struct dl_handle_deleter {
+    void operator()(HMODULE handle) {
+        FreeLibrary(handle);
+    }
+};
+
+#else
+
+using dl_handle = void;
+
+struct dl_handle_deleter {
+    void operator()(void * handle) {
+        dlclose(handle);
+    }
+};
+
+#endif
+
+using dl_handle_ptr = std::unique_ptr<dl_handle, dl_handle_deleter>;
+
+dl_handle * dl_load_library(const fs::path & path);
+void * dl_get_sym(dl_handle * handle, const char * name);
+const char * dl_error();
+

ggml/src/ggml-backend-reg.cpp

@@ -1,5 +1,6 @@
 #include "ggml-backend-impl.h"
 #include "ggml-backend.h"
+#include "ggml-backend-dl.h"
 #include "ggml-impl.h"
 #include <algorithm>
 #include <cstring>
@@ -98,72 +99,6 @@ static std::string path_str(const fs::path & path) {
     }
 }
 
-#ifdef _WIN32
-
-using dl_handle = std::remove_pointer_t<HMODULE>;
-
-struct dl_handle_deleter {
-    void operator()(HMODULE handle) {
-        FreeLibrary(handle);
-    }
-};
-
-static dl_handle * dl_load_library(const fs::path & path) {
-    // suppress error dialogs for missing DLLs
-    DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
-    SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
-
-    HMODULE handle = LoadLibraryW(path.wstring().c_str());
-
-    SetErrorMode(old_mode);
-
-    return handle;
-}
-
-static void * dl_get_sym(dl_handle * handle, const char * name) {
-    DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
-    SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
-
-    void * p = (void *) GetProcAddress(handle, name);
-
-    SetErrorMode(old_mode);
-
-    return p;
-}
-
-static const char * dl_error() {
-    return "";
-}
-
-#else
-
-using dl_handle = void;
-
-struct dl_handle_deleter {
-    void operator()(void * handle) {
-        dlclose(handle);
-    }
-};
-
-static void * dl_load_library(const fs::path & path) {
-    dl_handle * handle = dlopen(path.string().c_str(), RTLD_NOW | RTLD_LOCAL);
-
-    return handle;
-}
-
-static void * dl_get_sym(dl_handle * handle, const char * name) {
-    return dlsym(handle, name);
-}
-
-static const char * dl_error() {
-    const char *rslt = dlerror();
-    return rslt != nullptr ? rslt : "";
-}
-
-#endif
-
-using dl_handle_ptr = std::unique_ptr<dl_handle, dl_handle_deleter>;
-
 struct ggml_backend_reg_entry {
     ggml_backend_reg_t reg;
     dl_handle_ptr handle;

ggml/src/ggml-cuda/common.cuh

@@ -1122,15 +1122,17 @@ struct ggml_tensor_extra_gpu {
 #endif
 
 struct ggml_cuda_graph_node_properties {
-    void * node_address;
+    void * node_data;
     ggml_op node_op;
     int32_t flags;
     int64_t ne[GGML_MAX_DIMS];
     size_t nb[GGML_MAX_DIMS];
-    void * src_address[GGML_MAX_SRC];
+    void * src_data[GGML_MAX_SRC];
     int32_t op_params[GGML_MAX_OP_PARAMS / sizeof(int32_t)];
 };
 
+static_assert(std::is_trivial<ggml_cuda_graph_node_properties>::value, "ggml_cuda_graph_node_properties must be trivial");
+
 struct ggml_cuda_graph {
 #ifdef USE_CUDA_GRAPH
     ~ggml_cuda_graph() {
@@ -1150,6 +1152,12 @@ struct ggml_cuda_graph {
     int number_consecutive_updates = 0;
     std::vector<ggml_cuda_graph_node_properties> props;
 
+    // these are extra tensors (inputs) that participate in the ggml graph but are not nodes
+    // they properties also have to match in order to be able to safely reuse a CUDA graph
+    // ref: https://github.com/ggml-org/llama.cpp/pull/18583
+    // ref: https://github.com/ggml-org/llama.cpp/pull/19165
+    std::vector<ggml_cuda_graph_node_properties> extra;
+
     void record_update(bool use_graph, bool update_required) {
         if (use_graph && update_required) {
             number_consecutive_updates++;

ggml/src/ggml-cuda/fattn.cu

@@ -310,8 +310,6 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
         }
     }
 
-    const bool V_is_K_view = V->view_src && (V->view_src == K || (V->view_src == K->view_src && V->view_offs == K->view_offs));
-
     const int cc = ggml_cuda_info().devices[device].cc;
 
     switch (K->ne[0]) {
@@ -334,9 +332,6 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
             if (!gqa_opt_applies) {
                 return BEST_FATTN_KERNEL_NONE;
             }
-            if (!V_is_K_view) {
-                return BEST_FATTN_KERNEL_NONE;
-            }
             break;
         default:
             return BEST_FATTN_KERNEL_NONE;

ggml/src/ggml-cuda/ggml-cuda.cu

@@ -70,17 +70,18 @@
 #include <condition_variable>
 #include <cstddef>
 #include <cstdint>
-#include <float.h>
+#include <cfloat>
 #include <initializer_list>
 #include <limits>
 #include <map>
 #include <memory>
 #include <mutex>
-#include <stdarg.h>
-#include <stdio.h>
-#include <stdlib.h>
+#include <cstdarg>
+#include <cstdio>
+#include <cstdlib>
 #include <string>
 #include <vector>
+#include <unordered_set>
 
 static_assert(sizeof(half) == sizeof(ggml_fp16_t), "wrong fp16 size");
 
@@ -2916,7 +2917,8 @@ static bool ggml_cuda_graph_check_compability(ggml_cgraph * cgraph) {
 }
 
 static void ggml_cuda_graph_node_set_properties(ggml_cuda_graph_node_properties * props, ggml_tensor * node) {
-    props->node_address = node->data;
+    memset(props, 0, sizeof(ggml_cuda_graph_node_properties));
+    props->node_data = node->data;
     props->node_op = node->op;
     props->flags = node->flags;
     for (int i = 0; i < GGML_MAX_DIMS; i++) {
@@ -2924,14 +2926,17 @@ static void ggml_cuda_graph_node_set_properties(ggml_cuda_graph_node_properties
         props->nb[i] = node->nb[i];
     }
     for (int i = 0; i < GGML_MAX_SRC; i++) {
-        props->src_address[i] = node->src[i] ? node->src[i]->data : nullptr;
+        if (!node->src[i]) {
+            continue;
+        }
+
+        props->src_data[i] = node->src[i]->data;
     }
     memcpy(props->op_params, node->op_params, GGML_MAX_OP_PARAMS);
 }
 
 static bool ggml_cuda_graph_node_properties_match(ggml_tensor * node, ggml_cuda_graph_node_properties * props) {
-    if (node->data != props->node_address &&
-          node->op != GGML_OP_VIEW) {
+    if (node->data != props->node_data && node->op != GGML_OP_VIEW) {
         return false;
     }
 
@@ -2948,12 +2953,18 @@ static bool ggml_cuda_graph_node_properties_match(ggml_tensor * node, ggml_cuda_
         }
     }
 
-    for (int i = 0; i < GGML_MAX_SRC; i++) {
-        if (node->src[i] &&
-            node->src[i]->data != props->src_address[i] &&
-            node->op != GGML_OP_VIEW
-        ) {
-            return false;
+    if (node->op != GGML_OP_VIEW) {
+        for (int i = 0; i < GGML_MAX_SRC; i++) {
+            if (!node->src[i]) {
+                if (props->src_data[i] != nullptr) {
+                    return false;
+                }
+                continue;
+            }
+
+            if (node->src[i]->data != props->src_data[i]) {
+                return false;
+            }
         }
     }
 
@@ -2974,7 +2985,6 @@ static const void * ggml_cuda_graph_get_key(ggml_cgraph * cgraph) {
 }
 
 static bool ggml_cuda_graph_update_required(ggml_backend_cuda_context * cuda_ctx, ggml_cgraph * cgraph) {
-
     bool res = false;
 
     const void * graph_key = ggml_cuda_graph_get_key(cgraph);
@@ -2985,15 +2995,20 @@ static bool ggml_cuda_graph_update_required(ggml_backend_cuda_context * cuda_ctx
     }
 
     // Check if the graph size has changed
-    if (graph->props.size() != (size_t)cgraph->n_nodes + cgraph->n_leafs) {
+    if (graph->props.size() != (size_t)cgraph->n_nodes) {
         res = true;
-        graph->props.resize(cgraph->n_nodes + cgraph->n_leafs);
+        graph->props.resize(cgraph->n_nodes);
     }
 
     // Loop over nodes in GGML graph to determine if CUDA graph update is required
     // and store properties to allow this comparison for the next token
+    std::unordered_set<ggml_tensor *> seen_node;
+    std::vector<ggml_tensor *> srcs_extra;
     for (int i = 0; i < cgraph->n_nodes; i++) {
         bool props_match = true;
+
+        seen_node.insert(cgraph->nodes[i]);
+
         if (!res) {
             props_match = ggml_cuda_graph_node_properties_match(cgraph->nodes[i], &graph->props[i]);
         }
@@ -3001,17 +3016,31 @@ static bool ggml_cuda_graph_update_required(ggml_backend_cuda_context * cuda_ctx
             res = true;
         }
         ggml_cuda_graph_node_set_properties(&graph->props[i], cgraph->nodes[i]);
+
+        for (int src_idx = 0; src_idx < GGML_MAX_SRC; ++src_idx) {
+            ggml_tensor * src = cgraph->nodes[i]->src[src_idx];
+            if (src && seen_node.find(src) == seen_node.end()) {
+                srcs_extra.push_back(src);
+            }
+        }
     }
 
-    for (int i = 0; i < cgraph->n_leafs; i++) {
+    if (graph->extra.size() != (size_t) srcs_extra.size()) {
+        res = true;
+        graph->extra.resize(srcs_extra.size());
+    }
+
+    for (size_t i = 0; i < srcs_extra.size(); ++i) {
         bool props_match = true;
+
         if (!res) {
-            props_match = ggml_cuda_graph_node_properties_match(cgraph->leafs[i], &graph->props[cgraph->n_nodes + i]);
+            props_match = ggml_cuda_graph_node_properties_match(srcs_extra[i], &graph->extra[i]);
         }
+
         if (!props_match) {
             res = true;
         }
-        ggml_cuda_graph_node_set_properties(&graph->props[cgraph->n_nodes + i], cgraph->leafs[i]);
+        ggml_cuda_graph_node_set_properties(&graph->extra[i], srcs_extra[i]);
     }
 
     return res;

ggml/src/ggml-hexagon/CMakeLists.txt

@@ -1,7 +1,17 @@
+file(TO_CMAKE_PATH "${HEXAGON_SDK_ROOT}"   HEXAGON_SDK_ROOT)
+file(TO_CMAKE_PATH "${HEXAGON_TOOLS_ROOT}" HEXAGON_TOOLS_ROOT)
+
+if (NOT IS_DIRECTORY "${HEXAGON_SDK_ROOT}" OR NOT IS_DIRECTORY "${HEXAGON_TOOLS_ROOT}")
+    message(FATAL_ERROR "Make sure HEXAGON_SDK_ROOT and HEXAGON_TOOLS_ROOT point to the correct Hexagon SDK installation.")
+endif()
+
+message(STATUS "hexagon: using ${HEXAGON_SDK_ROOT} and ${HEXAGON_TOOLS_ROOT} for building libggml-htp skels")
+
 include(${HEXAGON_SDK_ROOT}/build/cmake/hexagon_fun.cmake)
 include(ExternalProject)
 
 option(GGML_HEXAGON_HTP_DEBUG "ggml-hexagon: enable HTP debug output" OFF)
+set(GGML_HEXAGON_HTP_CERT  "$ENV{HEXAGON_HTP_CERT}" CACHE PATH "ggml-hexagon: enable HTP library signing using certificate")
 set(GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE 128 CACHE STRING "ggml-hexagon: quantize group size (32, 64, or 128)")
 
 add_library(htp_iface OBJECT
@@ -25,56 +35,71 @@ else()
     target_link_options(htp_iface PUBLIC -ldl)
 endif()
 
-link_custom_library(htp_iface cdsprpc)
-link_custom_library(htp_iface rpcmem)
-
 set(TARGET_NAME ggml-hexagon)
 ggml_add_backend_library(${TARGET_NAME}
-    ggml-hexagon.cpp htp-utils.c htp-utils.h ../../include/ggml-hexagon.h)
+    ggml-hexagon.cpp
+    htp-drv.cpp
+    htp-drv.h
+    libdl.h
+    ../../include/ggml-hexagon.h)
 
 target_link_libraries(${TARGET_NAME} PRIVATE htp_iface)
 target_include_directories(${TARGET_NAME} PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/htp ${CMAKE_CURRENT_BINARY_DIR})
 
-# Build HTP bits
-set(HTP_CMAKE_ARGS
-    -DCMAKE_TOOLCHAIN_FILE=${CMAKE_CURRENT_SOURCE_DIR}/htp/cmake-toolchain.cmake
-    -DCMAKE_BUILD_TYPE=Release
-    -DCMAKE_INSTALL_LIBDIR=${CMAKE_CURRENT_BINARY_DIR}
-    -DHEXAGON_SDK_ROOT=$ENV{HEXAGON_SDK_ROOT}
-    -DHEXAGON_TOOLS_ROOT=$ENV{HEXAGON_TOOLS_ROOT}
-    -DHEXAGON_HTP_DEBUG=${GGML_HEXAGON_HTP_DEBUG}
-    -DGGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE=${GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE})
+# Build HTP skels
+set(HTP_SKELS)
+function(build_htp_skel V)
+    ExternalProject_Add(htp-${V}
+        SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
+        BUILD_BYPRODUCTS ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-${V}.so
+        CMAKE_ARGS
+            -DCMAKE_BUILD_TYPE=Release
+            -DCMAKE_TOOLCHAIN_FILE=${CMAKE_CURRENT_SOURCE_DIR}/htp/cmake-toolchain.cmake
+            -DCMAKE_INSTALL_LIBDIR=${CMAKE_CURRENT_BINARY_DIR}
+            -DHEXAGON_SDK_ROOT=${HEXAGON_SDK_ROOT}
+            -DHEXAGON_TOOLS_ROOT=${HEXAGON_TOOLS_ROOT}
+            -DHEXAGON_HTP_DEBUG=${GGML_HEXAGON_HTP_DEBUG}
+            -DGGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE=${GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE}
+            -DDSP_VERSION=${V}
+            -DPREBUILT_LIB_DIR="toolv19_${V}")
+    list(APPEND HTP_SKELS ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-${V}.so)
+    set(HTP_SKELS ${HTP_SKELS} PARENT_SCOPE)
+endfunction()
 
-ExternalProject_Add(htp-v68
-    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
-    CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v68 -DPREBUILT_LIB_DIR="toolv19_v68")
-
-ExternalProject_Add(htp-v69
-    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
-    CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v69 -DPREBUILT_LIB_DIR="toolv19_v69")
-
-ExternalProject_Add(htp-v73
-    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
-    CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v73 -DPREBUILT_LIB_DIR="toolv19_v73")
-
-ExternalProject_Add(htp-v75
-    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
-    CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v75 -DPREBUILT_LIB_DIR="toolv19_v75")
-
-ExternalProject_Add(htp-v79
-    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
-    CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v79 -DPREBUILT_LIB_DIR="toolv19_v79")
-
-ExternalProject_Add(htp-v81
-    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
-    CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v81 -DPREBUILT_LIB_DIR="toolv19_v81")
+build_htp_skel(v68)
+build_htp_skel(v69)
+build_htp_skel(v73)
+build_htp_skel(v75)
+build_htp_skel(v79)
+build_htp_skel(v81)
 
 # Install Hexagon skels required at runtime
-install(FILES
-    ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v68.so
-    ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v69.so
-    ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v73.so
-    ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v75.so
-    ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v79.so
-    ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v81.so
-    TYPE LIB)
+install(FILES ${HTP_SKELS} TYPE LIB)
+
+if (CMAKE_SYSTEM_NAME MATCHES Windows AND GGML_HEXAGON_HTP_CERT)
+    file(TO_CMAKE_PATH "$ENV{WINDOWS_SDK_BIN}/arm64"      WINSDK_BIN0_ARM64)
+    file(TO_CMAKE_PATH "$ENV{WINDOWS_SDK_BIN}/x86"        WINSDK_BIN0_X86)
+    file(TO_CMAKE_PATH "$ENV{WindowsSdkVerBinPath}/arm64" WINSDK_BIN1_ARM64)
+    file(TO_CMAKE_PATH "$ENV{WindowsSdkVerBinPath}/x86"   WINSDK_BIN1_X86)
+
+    set(WINSDK_PATHS ${WINSDK_BIN0_ARM64} ${WINSDK_BIN0_X86} ${WINSDK_BIN1_ARM64} ${WINSDK_BIN1_X86})
+
+    find_program(INF2CAT  NAMES inf2cat.exe  PATHS ${WINSDK_PATHS} REQUIRED)
+    find_program(SIGNTOOL NAMES signtool.exe PATHS ${WINSDK_PATHS} REQUIRED)
+
+    message(STATUS "hexagon: using ${GGML_HEXAGON_HTP_CERT} to sign libggml-htp skels")
+
+    set(LIBGGML_HTP_CAT ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp.cat)
+    add_custom_target(libggml-htp-cat
+        BYPRODUCTS ${LIBGGML_HTP_CAT}
+        DEPENDS libggml-htp.inf ${HTP_SKELS}
+        COMMAND ${CMAKE_COMMAND} -E copy ${CMAKE_CURRENT_SOURCE_DIR}/libggml-htp.inf ${CMAKE_CURRENT_BINARY_DIR}
+        COMMAND ${INF2CAT} /driver:${CMAKE_CURRENT_BINARY_DIR} /os:10_25H2_ARM64
+        COMMAND ${SIGNTOOL} sign /fd sha256 /f ${GGML_HEXAGON_HTP_CERT} ${LIBGGML_HTP_CAT}
+        COMMENT "generating and signing libggml-htp.cat file"
+        VERBATIM
+    )
+
+    add_dependencies(${TARGET_NAME} libggml-htp-cat)
+    install(FILES ${LIBGGML_HTP_CAT} TYPE LIB)
+endif()

ggml/src/ggml-hexagon/ggml-hexagon.cpp

@@ -14,9 +14,6 @@
 
 #ifdef _WIN32
 #    include <sal.h>
-#    ifndef _WINDOWS
-#        define _WINDOWS
-#    endif
 #else
 #    include <semaphore.h>
 #    include <unistd.h>
@@ -25,8 +22,6 @@
 #pragma clang diagnostic ignored "-Wnested-anon-types"
 #pragma clang diagnostic ignored "-Wgnu-anonymous-struct"
 
-#include "htp-utils.h"
-
 #include <AEEStdErr.h>
 #include <dspqueue.h>
 #include <rpcmem.h>
@@ -40,6 +35,7 @@
 #include "op-desc.h"
 #include "htp-msg.h"
 #include "htp_iface.h"
+#include "htp-drv.h"
 
 static size_t opt_ndev         = 1;
 static size_t opt_nhvx         = 0; // use all
@@ -150,9 +146,9 @@ void ggml_hexagon_session::enqueue(struct htp_general_req &req, struct dspqueue_
                              0,                       // flags - the framework will autoset this
                              n_bufs,                  // number of buffers
                              bufs,                    // buffer references
-                             sizeof(req),
+                             sizeof(req),             // Message length
                              (const uint8_t *) &req,  // Message
-                             1000000                  // Timeout
+                             DSPQUEUE_TIMEOUT         // Timeout
     );
 
     if (err != 0) {
@@ -182,13 +178,13 @@ void ggml_hexagon_session::flush() {
 
         // Read response packet from queue
         int err = dspqueue_read(q, &flags,
-                                   HTP_MAX_PACKET_BUFFERS,  // Maximum number of buffer references
-                                   &n_bufs,                 // Number of buffer references
-                                   bufs,                    // Buffer references
-                                   sizeof(rsp),             // Max message length
-                                   &rsp_size,               // Message length
-                                   (uint8_t *) &rsp,
-                                   1000000);                // Timeout
+                                HTP_MAX_PACKET_BUFFERS,  // Maximum number of buffer references
+                                &n_bufs,                 // Number of buffer references
+                                bufs,                    // Buffer references
+                                sizeof(rsp),             // Max message length
+                                &rsp_size,               // Message length
+                                (uint8_t *) &rsp,        // Message
+                                DSPQUEUE_TIMEOUT);       // Timeout
 
         if (err == AEE_EEXPIRED) {
             // TODO: might need to bail out if the HTP is stuck on something
@@ -269,13 +265,7 @@ struct ggml_backend_hexagon_buffer_context {
     ggml_backend_hexagon_buffer_context(ggml_hexagon_session * sess, size_t size, bool repack) {
         size += 4 * 1024;  // extra page for padding
 
-        if (rpcmem_alloc2) {
-            this->base = (uint8_t *) rpcmem_alloc2(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
-        } else {
-            GGML_LOG_INFO("ggml-hex: %s rpcmem_alloc2 not found, falling back to rpcmem_alloc\n", sess->name.c_str());
-            this->base = (uint8_t *) rpcmem_alloc(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
-        }
-
+        this->base = (uint8_t *) rpcmem_alloc2(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
         if (!this->base) {
             GGML_LOG_ERROR("ggml-hex: %s failed to allocate buffer : size %zu\n", sess->name.c_str(), size);
             throw std::runtime_error("ggml-hex: rpcmem_alloc failed (see log for details)");
@@ -2461,12 +2451,12 @@ static void ggml_backend_hexagon_free(ggml_backend_t backend) {
 }
 
 static inline bool op_reuse_src1(const ggml_tensor * op1, const ggml_tensor * op0) {
-    return (op0 && op0->src[1] == op1->src[1] && ggml_is_quantized(op0->src[0]->type) && ggml_is_quantized(op1->src[1]->type));
+    return (op0 && op0->src[1] == op1->src[1] && ggml_is_quantized(op0->src[0]->type));
 }
 
 static inline bool is_compute_op(ggml_tensor *node)
 {
-    return !(ggml_op_is_empty(node->op) || ggml_is_empty(node));
+    return !ggml_op_is_empty(node->op) && !ggml_is_empty(node) && (node->flags & GGML_TENSOR_FLAG_COMPUTE);
 }
 
 // scan the graph and figure out last compute op index
@@ -2488,7 +2478,7 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg
 
     const int last = last_compute_op(graph);
 
-    const struct ggml_tensor * prev_quant_op = nullptr;  // prev executed op with quantizer
+    const struct ggml_tensor * prev_op = nullptr;  // prev executed op
 
     for (int i = 0; i < graph->n_nodes; ++i) {
         ggml_tensor * node = graph->nodes[i];
@@ -2497,17 +2487,15 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg
             continue;
         }
 
-        if ((node->flags & GGML_TENSOR_FLAG_COMPUTE) == 0) {
-            continue;
-        }
-
         uint32_t flags = 0;
 
         // skip quantizer if src1 is reused
-        if (op_reuse_src1(node, prev_quant_op)) {
+        if (op_reuse_src1(node, prev_op)) {
             flags |= HTP_OPFLAGS_SKIP_QUANTIZE;
         }
 
+        prev_op = node;
+
         // ask for early notification for the last Op
         if (i == last) {
             flags |= HTP_OPFLAGS_EARLY_WAKEUP;
@@ -2520,7 +2508,6 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg
                 } else {
                     ggml_hexagon_dispatch_op<init_binary_req<false>>(sess, node, flags);
                 }
-                prev_quant_op = node;
                 break;
             case GGML_OP_MUL_MAT_ID:
                 if (ggml_is_quantized(node->src[0]->type)) {
@@ -2528,7 +2515,6 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg
                 } else {
                     ggml_hexagon_dispatch_op<init_binary_id_req<false>>(sess, node, flags);
                 }
-                prev_quant_op = node;
                 break;
             case GGML_OP_MUL:
             case GGML_OP_ADD:
@@ -2670,7 +2656,7 @@ static std::vector<int> ggml_hexagon_graph_optimize_reorder(const std::vector<no
         }
 
         // that many nodes forward to search for stackable nodes that can reuse VTCM
-        constexpr int N_FORWARD = 8;
+        constexpr int N_FORWARD = 16;
 
         for (int i1 = i0 + 1; i1 < i0 + N_FORWARD && i1 < n; i1++) {
             if (used[i1]) {
@@ -3056,10 +3042,12 @@ ggml_hexagon_registry::ggml_hexagon_registry(ggml_backend_reg_t reg) {
         }
     }
 
+#if defined(__ANDROID__)
     if (opt_arch < 75) {
         opt_ndev = 1;
         GGML_LOG_WARN("ggml-hex: forcing ndev to 1 for SoCs archs lower than v75.\n");
     }
+#endif
 
     GGML_LOG_INFO("ggml-hex: Hexagon Arch version v%d\n", opt_arch);
 
@@ -3156,6 +3144,8 @@ static void ggml_hexagon_init(ggml_backend_reg * reg) {
         opt_arch = strtoul(str_arch, NULL, 0);
     }
 
+    opt_hostbuf = str_hostbuf ? atoi(str_hostbuf) : 1;
+
     reg->context = new ggml_hexagon_registry(reg);
 
     HEX_VERBOSE("ggml-hex: size-of-general-req %zu size-of-general-rsp %zu\n", sizeof(struct htp_general_req),
@@ -3180,6 +3170,11 @@ ggml_backend_reg_t ggml_backend_hexagon_reg(void) {
         static std::mutex           mutex;
         std::lock_guard<std::mutex> lock(mutex);
         if (!initialized) {
+            auto nErr = htpdrv_init();
+            if (nErr != AEE_SUCCESS) {
+                return NULL;
+            }
+
             ggml_hexagon_init(&reg);
         }
 

ggml/src/ggml-hexagon/htp-drv.cpp

@@ -0,0 +1,418 @@
+// sample drv interface
+
+#pragma clang diagnostic ignored "-Wgnu-anonymous-struct"
+#pragma clang diagnostic ignored "-Wmissing-prototypes"
+#pragma clang diagnostic ignored "-Wsign-compare"
+
+#include <filesystem>
+#include <set>
+#include <sstream>
+#include <string>
+#ifdef _WIN32
+#   define WIN32_LEAN_AND_MEAN
+#   ifndef NOMINMAX
+#       define NOMINMAX
+#   endif
+#   include <windows.h>
+#   include <winevt.h>
+#else
+#    include <dlfcn.h>
+#    include <unistd.h>
+#endif
+#include "ggml-impl.h"
+#include "htp-drv.h"
+#include "libdl.h"
+
+#include <domain.h>
+
+//
+// Driver API types
+//
+
+typedef void * (*rpcmem_alloc_pfn_t)(int heapid, uint32_t flags, int size);
+typedef void * (*rpcmem_alloc2_pfn_t)(int heapid, uint32_t flags, size_t size);
+typedef void   (*rpcmem_free_pfn_t)(void * po);
+typedef int    (*rpcmem_to_fd_pfn_t)(void * po);
+
+typedef AEEResult (*dspqueue_create_pfn_t)(int                 domain,
+                                           uint32_t            flags,
+                                           uint32_t            req_queue_size,
+                                           uint32_t            resp_queue_size,
+                                           dspqueue_callback_t packet_callback,
+                                           dspqueue_callback_t error_callback,
+                                           void *              callback_context,
+                                           dspqueue_t *        queue);
+typedef AEEResult (*dspqueue_close_pfn_t)(dspqueue_t queue);
+typedef AEEResult (*dspqueue_export_pfn_t)(dspqueue_t queue, uint64_t *queue_id);
+typedef AEEResult (*dspqueue_write_pfn_t)(dspqueue_t queue, uint32_t flags,
+                                          uint32_t num_buffers,
+                                          struct dspqueue_buffer *buffers,
+                                          uint32_t message_length,
+                                          const uint8_t *message,
+                                          uint32_t timeout_us);
+typedef AEEResult (*dspqueue_read_pfn_t)(dspqueue_t queue, uint32_t *flags,
+                                         uint32_t max_buffers, uint32_t *num_buffers,
+                                         struct dspqueue_buffer *buffers,
+                                         uint32_t max_message_length,
+                                         uint32_t *message_length, uint8_t *message,
+                                         uint32_t timeout_us);
+
+typedef int (*fastrpc_mmap_pfn_t)(int domain, int fd, void *addr, int offset, size_t length, enum fastrpc_map_flags flags);
+typedef int (*fastrpc_munmap_pfn_t)(int domain, int fd, void *addr, size_t length);
+
+typedef int (*remote_handle64_open_pfn_t)(const char* name, remote_handle64 *ph);
+typedef int (*remote_handle64_invoke_pfn_t)(remote_handle64 h, uint32_t dwScalars, remote_arg *pra);
+typedef int (*remote_handle64_close_pfn_t)(remote_handle h);
+typedef int (*remote_handle_control_pfn_t)(uint32_t req, void* data, uint32_t datalen);
+typedef int (*remote_handle64_control_pfn_t)(remote_handle64 h, uint32_t req, void* data, uint32_t datalen);
+typedef int (*remote_session_control_pfn_t)(uint32_t req, void *data, uint32_t datalen);
+
+//
+// Driver API pfns
+//
+
+rpcmem_alloc_pfn_t  rpcmem_alloc_pfn  = nullptr;
+rpcmem_alloc2_pfn_t rpcmem_alloc2_pfn = nullptr;
+rpcmem_free_pfn_t   rpcmem_free_pfn   = nullptr;
+rpcmem_to_fd_pfn_t  rpcmem_to_fd_pfn  = nullptr;
+
+fastrpc_mmap_pfn_t   fastrpc_mmap_pfn   = nullptr;
+fastrpc_munmap_pfn_t fastrpc_munmap_pfn = nullptr;
+
+dspqueue_create_pfn_t dspqueue_create_pfn = nullptr;
+dspqueue_close_pfn_t  dspqueue_close_pfn  = nullptr;
+dspqueue_export_pfn_t dspqueue_export_pfn = nullptr;
+dspqueue_write_pfn_t  dspqueue_write_pfn  = nullptr;
+dspqueue_read_pfn_t   dspqueue_read_pfn   = nullptr;
+
+remote_handle64_open_pfn_t    remote_handle64_open_pfn    = nullptr;
+remote_handle64_invoke_pfn_t  remote_handle64_invoke_pfn  = nullptr;
+remote_handle64_close_pfn_t   remote_handle64_close_pfn   = nullptr;
+remote_handle_control_pfn_t   remote_handle_control_pfn   = nullptr;
+remote_handle64_control_pfn_t remote_handle64_control_pfn = nullptr;
+remote_session_control_pfn_t  remote_session_control_pfn  = nullptr;
+
+//
+// Driver API
+//
+
+void * rpcmem_alloc(int heapid, uint32_t flags, int size) {
+    return rpcmem_alloc_pfn(heapid, flags, size);
+}
+
+void * rpcmem_alloc2(int heapid, uint32_t flags, size_t size) {
+    if (rpcmem_alloc2_pfn) {
+        return rpcmem_alloc2_pfn(heapid, flags, size);
+    } else {
+        GGML_LOG_INFO("ggml-hex: rpcmem_alloc2 not found, falling back to rpcmem_alloc\n");
+        return rpcmem_alloc_pfn(heapid, flags, size);
+    }
+}
+
+void rpcmem_free(void * po) {
+    return rpcmem_free_pfn(po);
+}
+
+int rpcmem_to_fd(void * po) {
+    return rpcmem_to_fd_pfn(po);
+}
+
+HTPDRV_API int fastrpc_mmap(int domain, int fd, void * addr, int offset, size_t length, enum fastrpc_map_flags flags) {
+    return fastrpc_mmap_pfn(domain, fd, addr, offset, length, flags);
+}
+
+HTPDRV_API int fastrpc_munmap(int domain, int fd, void * addr, size_t length) {
+    return fastrpc_munmap_pfn(domain, fd, addr, length);
+}
+
+AEEResult dspqueue_create(int                 domain,
+                          uint32_t            flags,
+                          uint32_t            req_queue_size,
+                          uint32_t            resp_queue_size,
+                          dspqueue_callback_t packet_callback,
+                          dspqueue_callback_t error_callback,
+                          void *              callback_context,
+                          dspqueue_t *        queue) {
+    return dspqueue_create_pfn(domain, flags, req_queue_size, resp_queue_size, packet_callback, error_callback,
+                               callback_context, queue);
+}
+
+AEEResult dspqueue_close(dspqueue_t queue) {
+    return dspqueue_close_pfn(queue);
+}
+
+AEEResult dspqueue_export(dspqueue_t queue, uint64_t * queue_id) {
+    return dspqueue_export_pfn(queue, queue_id);
+}
+
+AEEResult dspqueue_write(dspqueue_t               queue,
+                         uint32_t                 flags,
+                         uint32_t                 num_buffers,
+                         struct dspqueue_buffer * buffers,
+                         uint32_t                 message_length,
+                         const uint8_t *          message,
+                         uint32_t                 timeout_us) {
+    return dspqueue_write_pfn(queue, flags, num_buffers, buffers, message_length, message, timeout_us);
+}
+
+AEEResult dspqueue_read(dspqueue_t               queue,
+                        uint32_t *               flags,
+                        uint32_t                 max_buffers,
+                        uint32_t *               num_buffers,
+                        struct dspqueue_buffer * buffers,
+                        uint32_t                 max_message_length,
+                        uint32_t *               message_length,
+                        uint8_t *                message,
+                        uint32_t                 timeout_us) {
+    return dspqueue_read_pfn(queue, flags, max_buffers, num_buffers, buffers, max_message_length, message_length,
+                             message, timeout_us);
+}
+
+HTPDRV_API int remote_handle64_open(const char * name, remote_handle64 * ph) {
+    return remote_handle64_open_pfn(name, ph);
+}
+
+HTPDRV_API int remote_handle64_invoke(remote_handle64 h, uint32_t dwScalars, remote_arg * pra) {
+    return remote_handle64_invoke_pfn(h, dwScalars, pra);
+}
+
+HTPDRV_API int remote_handle64_close(remote_handle64 h) {
+    return remote_handle64_close_pfn(h);
+}
+
+HTPDRV_API int remote_handle_control(uint32_t req, void * data, uint32_t datalen) {
+    return remote_handle_control_pfn(req, data, datalen);
+}
+
+HTPDRV_API int remote_handle64_control(remote_handle64 h, uint32_t req, void * data, uint32_t datalen) {
+    return remote_handle64_control_pfn(h, req, data, datalen);
+}
+
+HTPDRV_API int remote_session_control(uint32_t req, void * data, uint32_t datalen) {
+    return remote_session_control_pfn(req, data, datalen);
+}
+
+#ifdef _WIN32
+
+static std::string wstr_to_str(std::wstring_view wstr) {
+    std::string result;
+    if (wstr.empty()) {
+        return result;
+    }
+    auto bytes_needed = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS,
+                                            wstr.data(), (int) wstr.size(),
+                                            nullptr, 0, nullptr, nullptr);
+    if (bytes_needed == 0) {
+        GGML_LOG_ERROR("ggml-hex: WideCharToMultiByte failed. Error %lu\n", GetLastError());
+        throw std::runtime_error("Invalid wstring input");
+    }
+
+    result.resize(bytes_needed, '\0');
+    int bytes_written = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS,
+                                            wstr.data(), (int) wstr.size(),
+                                            result.data(), bytes_needed,
+                                            nullptr, nullptr);
+    if (bytes_written == 0) {
+        GGML_LOG_ERROR("ggml-hex: WideCharToMultiByte failed. Error %lu\n", GetLastError());
+        throw std::runtime_error("Wstring conversion failed");
+    }
+    return result;
+}
+
+static std::string get_driver_path() {
+    std::wstring serviceName = L"qcnspmcdm";
+    std::string result;
+
+    // Get a handle to the SCM database.
+    SC_HANDLE schSCManager = OpenSCManagerW(NULL, NULL, STANDARD_RIGHTS_READ);
+    if (nullptr == schSCManager) {
+        GGML_LOG_ERROR("ggml-hex: Failed to open SCManager. Error: %lu\n", GetLastError());
+        return result;
+    }
+
+    // Get a handle to the service.
+    SC_HANDLE schService = OpenServiceW(schSCManager,           // SCM database
+                                        serviceName.c_str(),    // name of service
+                                        SERVICE_QUERY_CONFIG);  // need query config access
+
+    if (nullptr == schService) {
+        GGML_LOG_ERROR("ggml-hex: Failed to open qcnspmcdm service. Error: %lu\n", GetLastError());
+        CloseServiceHandle(schSCManager);
+        return result;
+    }
+
+    // Store the size of buffer used as an output.
+    DWORD bufferSize;
+    if (!QueryServiceConfigW(schService, NULL, 0, &bufferSize) &&
+        (GetLastError() != ERROR_INSUFFICIENT_BUFFER)) {
+        GGML_LOG_ERROR("ggml-hex: Failed to query service config. Error: %lu\n", GetLastError());
+        CloseServiceHandle(schService);
+        CloseServiceHandle(schSCManager);
+        return result;
+    }
+    // Get the configuration of the service.
+    LPQUERY_SERVICE_CONFIGW serviceConfig =
+        static_cast<LPQUERY_SERVICE_CONFIGW>(LocalAlloc(LMEM_FIXED, bufferSize));
+    if (!QueryServiceConfigW(schService, serviceConfig, bufferSize, &bufferSize)) {
+        fprintf(stderr, "ggml-hex: Failed to query service config. Error: %lu\n", GetLastError());
+        LocalFree(serviceConfig);
+        CloseServiceHandle(schService);
+        CloseServiceHandle(schSCManager);
+        return result;
+    }
+
+    // Read the driver file path get its parent directory
+    std::wstring driverPath = std::wstring(serviceConfig->lpBinaryPathName);
+    driverPath = driverPath.substr(0, driverPath.find_last_of(L"\\"));
+
+    // Clean up resources
+    LocalFree(serviceConfig);
+    CloseServiceHandle(schService);
+    CloseServiceHandle(schSCManager);
+
+    // Driver path would contain invalid path string, like:
+    // \SystemRoot\System32\DriverStore\FileRepository\qcadsprpc8280.inf_arm64_c2b9460c9a072f37
+    // "\SystemRoot" should be replace with a correct one (e.g. C:\Windows)
+    const std::wstring systemRootPlaceholder = L"\\SystemRoot";
+    if (0 != driverPath.compare(0, systemRootPlaceholder.length(), systemRootPlaceholder)) {
+        GGML_LOG_ERROR("ggml-hex: String pattern not found in driver path.\n");
+        return result;
+    }
+
+    // Replace \SystemRoot with an absolute path from system ENV windir
+    const std::wstring systemRootEnv = L"windir";
+
+    // Query the number of wide charactors this variable requires
+    DWORD numWords = GetEnvironmentVariableW(systemRootEnv.c_str(), NULL, 0);
+    if (numWords == 0) {
+        GGML_LOG_ERROR("ggml-hex: Failed get systemRoot environment variable\n");
+        return result;
+    }
+
+    // Query the actual system root name from environment variable
+    std::vector<wchar_t> systemRoot(numWords + 1);
+    numWords = GetEnvironmentVariableW(systemRootEnv.c_str(), systemRoot.data(), numWords + 1);
+    if (numWords == 0) {
+        GGML_LOG_ERROR("ggml-hex: Failed to read windir environment variable\n");
+        return result;
+    }
+    driverPath.replace(0, systemRootPlaceholder.length(), std::wstring(systemRoot.data()));
+
+    return wstr_to_str(driverPath);
+}
+
+#endif
+
+using dl_handle_ptr = std::unique_ptr<dl_handle, dl_handle_deleter>;
+
+int htpdrv_init() {
+    static dl_handle_ptr lib_cdsp_rpc_handle = nullptr;
+    static bool initialized = false;
+#ifdef _WIN32
+    std::string drv_path = get_driver_path() + "\\" + "libcdsprpc.dll";
+#else
+    std::string drv_path = "libcdsprpc.so";
+#endif
+    if (initialized) {
+        GGML_LOG_INFO("ggml-hex: Driver already loaded\n");
+        return AEE_SUCCESS;
+    }
+    GGML_LOG_INFO("ggml-hex: Loading driver %s\n", drv_path.c_str());
+
+    fs::path path{ drv_path.c_str() };
+    dl_handle_ptr handle { dl_load_library(path) };
+    if (!handle) {
+        GGML_LOG_ERROR("ggml-hex: failed to load %s: %s\n", path.u8string().c_str(), dl_error());
+        return AEE_EUNABLETOLOAD;
+    }
+
+#define dlsym(drv, type, pfn, symbol, ignore)                               \
+    do {                                                                    \
+        pfn = (type) dl_get_sym(drv, #symbol);                              \
+        if (!ignore && nullptr == pfn) {                                    \
+            GGML_LOG_ERROR("ggml-hex: failed to dlsym %s\n", #symbol);      \
+            return AEE_EUNABLETOLOAD;                                       \
+        }                                                                   \
+    } while (0)
+
+    dlsym(handle.get(), rpcmem_alloc_pfn_t, rpcmem_alloc_pfn, rpcmem_alloc, false);
+    dlsym(handle.get(), rpcmem_alloc2_pfn_t, rpcmem_alloc2_pfn, rpcmem_alloc2, true);
+    dlsym(handle.get(), rpcmem_free_pfn_t, rpcmem_free_pfn, rpcmem_free, false);
+    dlsym(handle.get(), rpcmem_to_fd_pfn_t, rpcmem_to_fd_pfn, rpcmem_to_fd, false);
+    dlsym(handle.get(), fastrpc_mmap_pfn_t, fastrpc_mmap_pfn, fastrpc_mmap, false);
+    dlsym(handle.get(), fastrpc_munmap_pfn_t, fastrpc_munmap_pfn, fastrpc_munmap, false);
+    dlsym(handle.get(), dspqueue_create_pfn_t, dspqueue_create_pfn, dspqueue_create, false);
+    dlsym(handle.get(), dspqueue_close_pfn_t, dspqueue_close_pfn, dspqueue_close, false);
+    dlsym(handle.get(), dspqueue_export_pfn_t, dspqueue_export_pfn, dspqueue_export, false);
+    dlsym(handle.get(), dspqueue_write_pfn_t, dspqueue_write_pfn, dspqueue_write, false);
+    dlsym(handle.get(), dspqueue_read_pfn_t, dspqueue_read_pfn, dspqueue_read, false);
+    dlsym(handle.get(), remote_handle64_open_pfn_t, remote_handle64_open_pfn, remote_handle64_open, false);
+    dlsym(handle.get(), remote_handle64_invoke_pfn_t, remote_handle64_invoke_pfn, remote_handle64_invoke, false);
+    dlsym(handle.get(), remote_handle_control_pfn_t, remote_handle_control_pfn, remote_handle_control, false);
+    dlsym(handle.get(), remote_handle64_control_pfn_t, remote_handle64_control_pfn, remote_handle64_control, false);
+    dlsym(handle.get(), remote_session_control_pfn_t, remote_session_control_pfn, remote_session_control, false);
+    dlsym(handle.get(), remote_handle64_close_pfn_t, remote_handle64_close_pfn, remote_handle64_close, false);
+
+    lib_cdsp_rpc_handle = std::move(handle);
+    initialized         = true;
+
+    return AEE_SUCCESS;
+}
+
+domain * get_domain(int domain_id) {
+    int i    = 0;
+    int size = sizeof(supported_domains) / sizeof(domain);
+
+    for (i = 0; i < size; i++) {
+        if (supported_domains[i].id == domain_id) {
+            return &supported_domains[i];
+        }
+    }
+
+    return NULL;
+}
+
+int get_hex_arch_ver(int domain, int * arch) {
+    if (!remote_handle_control_pfn) {
+        GGML_LOG_ERROR("ggml-hex: remote_handle_control is not supported on this device\n");
+        return AEE_EUNSUPPORTEDAPI;
+    }
+
+    struct remote_dsp_capability arch_ver;
+    arch_ver.domain       = (uint32_t) domain;
+    arch_ver.attribute_ID = ARCH_VER;
+    arch_ver.capability   = (uint32_t) 0;
+
+    int err = remote_handle_control(DSPRPC_GET_DSP_INFO, &arch_ver, sizeof(arch_ver));
+    if ((err & 0xff) == (AEE_EUNSUPPORTEDAPI & 0xff)) {
+        GGML_LOG_ERROR("ggml-hex: FastRPC capability API is not supported on this device\n");
+        return AEE_EUNSUPPORTEDAPI;
+    }
+
+    if (err != AEE_SUCCESS) {
+        GGML_LOG_ERROR("ggml-hex: FastRPC capability query failed (err %d)\n", err);
+        return err;
+    }
+
+    switch (arch_ver.capability & 0xff) {
+        case 0x68:
+            *arch = 68;
+            return 0;
+        case 0x69:
+            *arch = 69;
+            return 0;
+        case 0x73:
+            *arch = 73;
+            return 0;
+        case 0x75:
+            *arch = 75;
+            return 0;
+        case 0x79:
+            *arch = 79;
+            return 0;
+        case 0x81:
+            *arch = 81;
+            return 0;
+    }
+    return -1;
+}

ggml/src/ggml-hexagon/htp-drv.h

@@ -0,0 +1,121 @@
+#pragma once
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifdef _WIN32
+#    pragma clang diagnostic ignored "-Wignored-attributes"
+#endif
+
+#include <AEEStdErr.h>
+#include <rpcmem.h>
+#include <remote.h>
+#include <dspqueue.h>
+
+#if defined(_WIN32) && !defined(__MINGW32__)
+#    ifdef GGML_BACKEND_BUILD
+#        define HTPDRV_API __declspec(dllexport) extern
+#    else
+#        define HTPDRV_API __declspec(dllimport) extern
+#    endif
+#else
+#    define HTPDRV_API __attribute__ ((visibility ("default"))) extern
+#endif
+
+/* Offset to differentiate HLOS and Hexagon error codes.
+   Stores the value of AEE_EOFFSET for Hexagon. */
+#ifndef DSP_OFFSET
+#    define DSP_OFFSET 0x80000400
+#endif
+
+/* Errno for connection reset by peer. */
+#ifndef ECONNRESET
+#    ifdef __hexagon__
+#        define ECONNRESET 104
+#    endif
+#endif
+
+/* Abstraction of different OS specific sleep APIs.
+   SLEEP accepts input in seconds. */
+#ifndef SLEEP
+#    ifdef __hexagon__
+#        define SLEEP(x)                      \
+            { /* Do nothing for simulator. */ \
+            }
+#    else
+#        ifdef _WIN32
+#            define SLEEP(x) Sleep(1000 * x) /* Sleep accepts input in milliseconds. */
+#        else
+#            define SLEEP(x) sleep(x)        /* sleep accepts input in seconds. */
+#        endif
+#    endif
+#endif
+
+/* Include windows specific header files. */
+#ifdef _WIN32
+#    include <windows.h>
+#    include <sysinfoapi.h>
+#    define _CRT_SECURE_NO_WARNINGS         1
+#    define _WINSOCK_DEPRECATED_NO_WARNINGS 1
+#endif
+
+/* Includes and defines for all HLOS except windows */
+#if !defined(__hexagon__) && !defined(_WIN32)
+#    include "unistd.h"
+
+#    include <sys/time.h>
+#endif
+
+/* Includes and defines for Hexagon and all HLOS except Windows. */
+#if !defined(_WIN32)
+/* Weak reference to remote symbol for compilation. */
+#    pragma weak remote_session_control
+#    pragma weak remote_handle_control
+#    pragma weak remote_handle64_control
+#    pragma weak fastrpc_mmap
+#    pragma weak fastrpc_munmap
+#    pragma weak rpcmem_alloc2
+#endif
+
+#if !defined(_WIN32)
+#    pragma weak remote_system_request
+#endif
+
+#ifdef _WIN32
+#     define DSPQUEUE_TIMEOUT DSPQUEUE_TIMEOUT_NONE
+#else
+#     define DSPQUEUE_TIMEOUT 1000000
+#endif
+
+/**
+ * htpdrv_init API: driver interface entry point
+ *
+ * @return      Return AEE error codes as defined in Hexagon SDK.
+ */
+HTPDRV_API int htpdrv_init(void);
+
+/**
+ * get_domain API: get domain struct from domain value.
+ *
+ * @param[in]  domain value of a domain
+ * @return     Returns domain struct of the domain if it is supported or else
+ *             returns NULL.
+ *
+ */
+HTPDRV_API domain * get_domain(int domain_id);
+
+/**
+ * get_hex_arch_ver API: query the Hexagon processor architecture version information
+ *
+ * @param[in]   domain_id value of a domain
+ * @param[out]  Arch version (73, 75, ...)
+ * @return      0 if query is successful.
+ *              non-zero if error, return value points to the error.
+ *
+ */
+HTPDRV_API int get_hex_arch_ver(int domain, int * arch);
+
+#ifdef __cplusplus
+}
+#endif

ggml/src/ggml-hexagon/htp-utils.c

@@ -1,454 +0,0 @@
-
-#pragma clang diagnostic ignored "-Wgnu-anonymous-struct"
-#pragma clang diagnostic ignored "-Wmissing-prototypes"
-#pragma clang diagnostic ignored "-Wsign-compare"
-
-#define GGML_COMMON_IMPL_C
-#include "ggml-backend-impl.h"
-#include "ggml-common.h"
-#include "ggml-hexagon.h"
-#include "ggml-impl.h"
-
-#include "htp-utils.h"
-
-#include <domain.h>
-#include <remote.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-domain * get_domain(int domain_id) {
-    int i    = 0;
-    int size = sizeof(supported_domains) / sizeof(domain);
-
-    for (i = 0; i < size; i++) {
-        if (supported_domains[i].id == domain_id) {
-            return &supported_domains[i];
-        }
-    }
-
-    return NULL;
-}
-
-bool is_valid_domain_id(int domain_id, int compute_only) {
-    int i    = 0;
-    int size = sizeof(supported_domains) / sizeof(domain);
-
-    if (compute_only) {
-        return is_CDSP(domain_id);
-    }
-
-    for (i = 0; i < size; i++) {
-        if (supported_domains[i].id == domain_id) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-int get_domains_info(char * domain_type, int * num_domains, fastrpc_domain ** domains_info) {
-    int nErr    = AEE_SUCCESS;
-    int ss_info = 0;
-    if (domain_type != NULL) {
-        if (strcmp(domain_type, "LPASS") == 0) {
-            ss_info = FASTRPC_LPASS;
-        } else if (strcmp(domain_type, "HPASS") == 0) {
-            ss_info = FASTRPC_HPASS;
-        } else {
-            ss_info = FASTRPC_NSP;
-        }
-    }
-    system_req_payload req  = { 0 };
-    req.id                  = FASTRPC_GET_DOMAINS;
-    req.sys.domains         = NULL;
-    fastrpc_domain * domain = NULL;
-    if (ss_info != 0) {
-        req.sys.flags = DOMAINS_LIST_FLAGS_SET_TYPE(req.sys.flags, ss_info);
-    } else {
-        req.sys.flags = 0;
-    }
-#ifdef _WIN32
-    nErr = AEE_EUNSUPPORTED;
-    goto bail;
-#endif
-    if (remote_system_request) {
-        nErr = remote_system_request(&req);
-        if (nErr != AEE_SUCCESS) {
-            GGML_LOG_ERROR("Failure in remote_system_request call: %d.\n", nErr);
-            goto bail;
-        }
-        // Allocate memory for domain-info array
-        req.sys.max_domains = req.sys.num_domains;
-        if ((req.sys.domains = calloc(req.sys.num_domains, sizeof(fastrpc_domain))) == NULL) {
-            nErr = AEE_ENOMEMORY;
-            GGML_LOG_ERROR("Unable to allocate memory for req.sys.domains");
-            goto bail;
-        }
-
-        nErr = remote_system_request(&req);
-        if (nErr != AEE_SUCCESS) {
-            GGML_LOG_ERROR("Failure in remote_system_request call: %d.\n", nErr);
-            goto bail;
-        }
-
-        for (int i = 0; i < req.sys.num_domains; i++) {
-            // Verify that only requested type domains were returned
-            domain = &req.sys.domains[i];
-            if (domain->type != ss_info && domain_type != NULL) {
-                nErr = -1;
-                GGML_LOG_ERROR("Incorrect data received from remote_system_request.\n");
-                goto bail;
-            }
-        }
-        *domains_info = req.sys.domains;
-        *num_domains  = req.sys.num_domains;
-    } else {
-        nErr = AEE_EUNSUPPORTED;
-        goto bail;
-    }
-bail:
-    if (nErr && !req.sys.domains) {
-        free(req.sys.domains);
-    }
-    return nErr;
-}
-
-int get_effective_domain_id(char * domain_name, int session_id, int * effec_domain_id) {
-    int                              err  = 0;
-    remote_rpc_effective_domain_id_t sess = { 0 };
-
-    sess.domain_name     = domain_name;
-    sess.domain_name_len = strlen(domain_name);
-    sess.session_id      = session_id;
-
-    err = remote_session_control(FASTRPC_GET_EFFECTIVE_DOMAIN_ID, &sess, sizeof(sess));
-    if (err) {
-        GGML_LOG_ERROR("Error 0x%x: failed to get effective domain id for %s, session id %d\n", err, sess.domain_name,
-               session_id);
-        return err;
-    }
-
-    *effec_domain_id = sess.effective_domain_id;
-    return err;
-}
-
-int get_dsp_support(int * domain) {
-    int nErr = AEE_SUCCESS;
-    *domain  = CDSP_DOMAIN_ID;  // DSP domain default value is CDSP_DOMAIN_ID
-
-    if (remote_handle_control) {
-        struct remote_dsp_capability dsp_capability_domain = { CDSP_DOMAIN_ID, DOMAIN_SUPPORT, 0 };
-        nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_domain, sizeof(struct remote_dsp_capability));
-        if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-            GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
-            goto bail;
-        }
-
-        if (dsp_capability_domain.capability == 0) {
-            dsp_capability_domain.domain       = ADSP_DOMAIN_ID;  // Check for ADSP support.
-            dsp_capability_domain.attribute_ID = DOMAIN_SUPPORT;
-            dsp_capability_domain.capability   = 0;
-            nErr                               = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_domain,
-                                                                       sizeof(struct remote_dsp_capability));
-            if (dsp_capability_domain.capability) {
-                *domain = ADSP_DOMAIN_ID;  // For targets like Agatti (not having cDSP), domain is ADSP_DOMAIN_ID
-            }
-        }
-
-        if (nErr != AEE_SUCCESS) {
-            GGML_LOG_ERROR("\nget_dsp_support failed with Error 0x%x\n", nErr);
-            goto bail;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
-    }
-
-bail:
-    return nErr;
-}
-
-int get_vtcm_info(int domain, uint32_t * capability, uint32_t attr) {
-    int nErr    = AEE_SUCCESS;
-    *capability = 0;
-
-    if (attr == VTCM_PAGE || attr == VTCM_COUNT) {
-    } else {
-        nErr = AEE_EBADPARM;
-        GGML_LOG_ERROR("Unsupported attr. Only VTCM_PAGE and VTCM_COUNT supported\n");
-        goto bail;
-    }
-    if (remote_handle_control) {
-        if (domain == ADSP_DOMAIN_ID || domain == CDSP_DOMAIN_ID) {
-            /*
-            * Query the DSP for VTCM information
-            * Since the ADSP does not have a dedicated VTCM, we expect the output to be 0
-            */
-            struct remote_dsp_capability dsp_capability_vtcm_dsp;
-            dsp_capability_vtcm_dsp.domain       = (uint32_t) domain;
-            dsp_capability_vtcm_dsp.attribute_ID = attr;
-            dsp_capability_vtcm_dsp.capability   = (uint32_t) 0;
-            nErr                                 = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_vtcm_dsp,
-                                                                         sizeof(struct remote_dsp_capability));
-            if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-                GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
-                GGML_LOG_ERROR("Running the usecase without checking the capability\n");
-                nErr = AEE_SUCCESS;
-                goto bail;
-            } else if (nErr == AEE_SUCCESS) {
-                *capability = dsp_capability_vtcm_dsp.capability;
-            } else {
-                GGML_LOG_ERROR("\nget_vtcm_info failed with Error 0x%x\n", nErr);
-                goto bail;
-            }
-        } else {
-            nErr = AEE_EUNSUPPORTED;
-            GGML_LOG_ERROR("Unsupported domain %d\n", domain);
-            goto bail;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
-    }
-
-bail:
-    return nErr;
-}
-
-bool is_unsignedpd_supported(int domain_id) {
-    int nErr = AEE_SUCCESS;
-    if (remote_handle_control) {
-        struct remote_dsp_capability dsp_capability_domain = { domain_id, UNSIGNED_PD_SUPPORT, 0 };
-        nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_domain, sizeof(struct remote_dsp_capability));
-        if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-            GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device. Falling back to signed pd.\n");
-            return false;
-        }
-        if (nErr) {
-            GGML_LOG_ERROR("\nERROR 0x%x: FastRPC Capability API failed. Falling back to signed pd.", nErr);
-            return false;
-        }
-        if (dsp_capability_domain.capability == 1) {
-            return true;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device. Falling back to signed pd.\n");
-        return false;
-    }
-    return false;
-}
-
-bool get_unsignedpd_support(void) {
-    return is_unsignedpd_supported(CDSP_DOMAIN_ID);
-}
-
-bool is_async_fastrpc_supported(int domain) {
-    int nErr = AEE_SUCCESS;
-    if (remote_handle_control) {
-        if (domain == CDSP_DOMAIN_ID) {
-            /*
-            * Query the DSP for ASYNC_FASTRPC_SUPPORT information
-            * Async fastrpc is supported only on CDSP
-            */
-            struct remote_dsp_capability dsp_capability_async_support;
-            dsp_capability_async_support.domain       = (uint32_t) domain;
-            dsp_capability_async_support.attribute_ID = ASYNC_FASTRPC_SUPPORT;
-            dsp_capability_async_support.capability   = (uint32_t) 0;
-            nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_async_support,
-                                         sizeof(struct remote_dsp_capability));
-            if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-                GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
-                GGML_LOG_ERROR("Running the usecase without checking the capability\n");
-                nErr = AEE_SUCCESS;
-                goto bail;
-            } else if (dsp_capability_async_support.capability == 1) {
-                return true;
-            }
-            if (nErr != AEE_SUCCESS) {
-                GGML_LOG_ERROR("\nis_async_fastrpc_supported failed with Error 0x%x\n", nErr);
-                goto bail;
-            }
-        } else {
-            nErr = AEE_EUNSUPPORTED;
-            GGML_LOG_ERROR("Async fastrpc is not supported on domain %d\n", domain);
-            goto bail;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
-    }
-
-bail:
-    return false;
-}
-
-bool is_status_notification_supported(int domain) {
-    int nErr = AEE_SUCCESS;
-
-    if (remote_handle_control) {
-        /*
-        * Query the DSP for STATUS_NOTIFICATION_SUPPORT information
-        * DSP User PD status notification Support
-        */
-        struct remote_dsp_capability dsp_capability_status_notification_support;
-        dsp_capability_status_notification_support.domain       = (uint32_t) domain;
-        dsp_capability_status_notification_support.attribute_ID = STATUS_NOTIFICATION_SUPPORT;
-        dsp_capability_status_notification_support.capability   = (uint32_t) 0;
-        nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_status_notification_support,
-                                     sizeof(struct remote_dsp_capability));
-        if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-            GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
-            GGML_LOG_ERROR("Running the usecase without checking the capability\n");
-            nErr = AEE_SUCCESS;
-            goto bail;
-        } else if (dsp_capability_status_notification_support.capability == 1) {
-            return true;
-        }
-        if (nErr != AEE_SUCCESS) {
-            GGML_LOG_ERROR("\nis_status_notification_supported failed with Error 0x%x\n", nErr);
-            goto bail;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
-    }
-
-bail:
-    return false;
-}
-
-int get_hmx_support_info(int domain, uint32_t * capability, uint32_t attr) {
-    int nErr    = AEE_SUCCESS;
-    *capability = 0;
-
-    if (attr != HMX_SUPPORT_SPATIAL && attr != HMX_SUPPORT_DEPTH) {
-        nErr = AEE_EBADPARM;
-        GGML_LOG_ERROR("Unsupported attr. Only HMX_SUPPORT_SPATIAL and HMX_SUPPORT_DEPTH supported\n");
-        goto bail;
-    }
-    if (remote_handle_control) {
-        if (domain == CDSP_DOMAIN_ID) {
-            /*
-            * Query the DSP for HMX SUPPORT information
-            * HMX is supported on CDSP only
-            */
-            struct remote_dsp_capability dsp_capability_hmx_dsp;
-            dsp_capability_hmx_dsp.domain       = (uint32_t) domain;
-            dsp_capability_hmx_dsp.attribute_ID = attr;
-            dsp_capability_hmx_dsp.capability   = (uint32_t) 0;
-            nErr                                = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_hmx_dsp,
-                                                                        sizeof(struct remote_dsp_capability));
-            if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-                GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
-                GGML_LOG_ERROR("Running the usecase without checking the capability\n");
-                nErr = AEE_SUCCESS;
-                goto bail;
-            } else if (nErr == AEE_SUCCESS) {
-                *capability = dsp_capability_hmx_dsp.capability;
-            } else {
-                GGML_LOG_ERROR("\nget_hmx_support_info failed with Error 0x%x\n", nErr);
-                goto bail;
-            }
-        } else {
-            nErr = AEE_EUNSUPPORTED;
-            GGML_LOG_ERROR("HMX support is not there for domain %d\n", domain);
-            goto bail;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
-    }
-
-bail:
-    return nErr;
-}
-
-int get_hex_arch_ver(int domain, int * arch) {
-    if (!remote_handle_control) {
-        GGML_LOG_ERROR("ggml-hex: remote_handle_control is not supported on this device\n");
-        return AEE_EUNSUPPORTEDAPI;
-    }
-
-    struct remote_dsp_capability arch_ver;
-    arch_ver.domain       = (uint32_t) domain;
-    arch_ver.attribute_ID = ARCH_VER;
-    arch_ver.capability   = (uint32_t) 0;
-
-    int err = remote_handle_control(DSPRPC_GET_DSP_INFO, &arch_ver, sizeof(arch_ver));
-    if ((err & 0xff) == (AEE_EUNSUPPORTEDAPI & 0xff)) {
-        GGML_LOG_ERROR("ggml-hex: FastRPC capability API is not supported on this device\n");
-        return AEE_EUNSUPPORTEDAPI;
-    }
-
-    if (err != AEE_SUCCESS) {
-        GGML_LOG_ERROR("ggml-hex: FastRPC capability query failed (err %d)\n", err);
-        return err;
-    }
-
-    switch (arch_ver.capability & 0xff) {
-        case 0x68:
-            *arch = 68;
-            return 0;
-        case 0x69:
-            *arch = 69;
-            return 0;
-        case 0x73:
-            *arch = 73;
-            return 0;
-        case 0x75:
-            *arch = 75;
-            return 0;
-        case 0x79:
-            *arch = 79;
-            return 0;
-        case 0x81:
-            *arch = 81;
-            return 0;
-    }
-    return -1;
-}
-
-int get_hvx_support_info(int domain, uint32_t * capability, uint32_t attr) {
-    int nErr    = AEE_SUCCESS;
-    *capability = 0;
-
-    if (remote_handle_control) {
-        if (domain == CDSP_DOMAIN_ID) {
-            /*
-            * Query the DSP for HVX SUPPORT information
-            * HVX is supported on CDSP only
-            */
-            struct remote_dsp_capability dsp_capability_hvx_dsp;
-            dsp_capability_hvx_dsp.domain       = (uint32_t) domain;
-            dsp_capability_hvx_dsp.attribute_ID = attr;
-            dsp_capability_hvx_dsp.capability   = (uint32_t) 0;
-            nErr                                = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_hvx_dsp,
-                                                                        sizeof(struct remote_dsp_capability));
-            if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
-                GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
-                GGML_LOG_ERROR("Running the usecase without checking the capability\n");
-                nErr = AEE_SUCCESS;
-                goto bail;
-            } else if (nErr == AEE_SUCCESS) {
-                *capability = dsp_capability_hvx_dsp.capability;
-            } else {
-                GGML_LOG_ERROR("\nget_hvx_support_info failed with Error 0x%x\n", nErr);
-                goto bail;
-            }
-        } else {
-            nErr = AEE_EUNSUPPORTED;
-            GGML_LOG_ERROR("HVX support is not available on domain %d\n", domain);
-            goto bail;
-        }
-    } else {
-        nErr = AEE_EUNSUPPORTEDAPI;
-        GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
-    }
-
-bail:
-    return nErr;
-}

ggml/src/ggml-hexagon/htp-utils.h

@@ -1,221 +0,0 @@
-#ifndef HTP_UTILS_H
-#define HTP_UTILS_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include <AEEStdErr.h>
-#include <inttypes.h>
-#include <remote.h>
-#include <rpcmem.h>
-#include <stdbool.h>
-
-/* Offset to differentiate HLOS and Hexagon error codes.
-   Stores the value of AEE_EOFFSET for Hexagon. */
-#ifndef DSP_OFFSET
-#    define DSP_OFFSET 0x80000400
-#endif
-
-/* Errno for connection reset by peer. */
-#ifndef ECONNRESET
-#    ifdef __hexagon__
-#        define ECONNRESET 104
-#    endif
-#endif
-
-/* Abstraction of different OS specific sleep APIs.
-   SLEEP accepts input in seconds. */
-#ifndef SLEEP
-#    ifdef __hexagon__
-#        define SLEEP(x)                      \
-            { /* Do nothing for simulator. */ \
-            }
-#    else
-#        ifdef _WINDOWS
-#            define SLEEP(x) Sleep(1000 * x) /* Sleep accepts input in milliseconds. */
-#        else
-#            define SLEEP(x) sleep(x)        /* sleep accepts input in seconds. */
-#        endif
-#    endif
-#endif
-
-/* Include windows specific header files. */
-#ifdef _WINDOWS
-#    include <sysinfoapi.h>
-#    include <windows.h>
-#    define _CRT_SECURE_NO_WARNINGS         1
-#    define _WINSOCK_DEPRECATED_NO_WARNINGS 1
-/* Including this file for custom implementation of getopt function. */
-#    include "getopt_custom.h"
-#endif
-
-/* Includes and defines for all HLOS except windows */
-#if !defined(__hexagon__) && !defined(_WINDOWS)
-#    include "unistd.h"
-
-#    include <sys/time.h>
-#endif
-
-/* Includes and defines for Hexagon and all HLOS except Windows. */
-#if !defined(_WINDOWS)
-/* Weak reference to remote symbol for compilation. */
-#    pragma weak remote_session_control
-#    pragma weak remote_handle_control
-#    pragma weak remote_handle64_control
-#    pragma weak fastrpc_mmap
-#    pragma weak fastrpc_munmap
-#    pragma weak rpcmem_alloc2
-#endif
-
-#if !defined(_WINDOWS)
-#    pragma weak remote_system_request
-#endif
-/**
- * Wrapper for FastRPC Capability API: query DSP support.
- *
- * @param[out]  domain pointer to supported domain.
- * @return      0          if query is successful.
- *              non-zero   if error, return value points to the error.
- */
-int get_dsp_support(int * domain);
-
-/**
- * Wrapper for FastRPC Capability API: query VTCM information.
- *
- * @param[in]   domain value of domain in the queried.
- * @param[out]  capability capability value of the attribute queried.
- * @param[in]   attr value of the attribute to the queried.
- * @return      0          if query is successful.
- *              non-zero   if error, return value points to the error.
- */
-int get_vtcm_info(int domain, uint32_t * capability, uint32_t attr);
-
-/**
- * Wrapper for FastRPC Capability API: query unsigned pd support on CDSP domain.
- *
- * @return      true          if unsigned pd is supported.
- *              false         if unsigned pd is not supported, capability query failed.
- */
-
-bool get_unsignedpd_support(void);
-
-/**
- * Wrapper for FastRPC Capability API: query unsigned pd support.
- *
- * @param[in]   domain value of domain in the queried.
- * @return      true          if unsigned pd is supported.
- *              false         if unsigned pd is not supported, capability query failed.
- */
-
-bool is_unsignedpd_supported(int domain_id);
-
-/**
- * is_valid_domain_id API: query a domain id is valid.
- *
- * @param[in]   domain value of domain in the queried.
- * @param[in]   compute_only value of domain is only compared with CDSP domains supported by the target when enabled.
- * @return      true          if value of domain is valid.
- *              false         if value of domain is not valid.
- */
-
-bool is_valid_domain_id(int domain_id, int compute_only);
-
-/**
- * get_domain API: get domain struct from domain value.
- *
- * @param[in]  domain value of a domain
- * @return     Returns domain struct of the domain if it is supported or else
- *             returns NULL.
- *
- */
-
-domain * get_domain(int domain_id);
-
-/**
- * get_domains_info API: get information for all the domains available on the device
- *
- * @param[in]  domain_type pointer to domain type
- * @param[in]  num_domains pointer to number of domains
- * @param[in]  domains_info pointer to save discovered domains information.
- * @return     0 if query is successful.
- *              non-zero if error, return value points to the error.
- *
- * It is user's responsibility to free the memory used to store the domains info whose address is present in domains_info before closing the application.
- *
- */
-
-int get_domains_info(char * domain_type, int * num_domains, fastrpc_domain ** domains_info);
-
-/**
- * get_effective_domain_id API: get effective domain id for given session id
- *
- * @param[in]  domain_name pointer to domain name
- * @param[in]  session_id
- * @param[in]  effec_domain_id pointer to save obtained effective domain id.
- * @return     0 if query is successful.
- *              non-zero if error, return value points to the error.
- *
- */
-
-int get_effective_domain_id(char * domain_name, int session_id, int * effec_domain_id);
-
-/**
- * is_async_fastrpc_supported API: query a domain id has async fastrpc supported or not
- *
- * @param[in]  domain_id value of a domain
- * @return     Returns true or false stating support of Async FastRPC
- *
- */
-
-bool is_async_fastrpc_supported(int domain_id);
-
-/**
- * is_status_notification_supported API: query the DSP for STATUS_NOTIFICATION_SUPPORT information
- *
- * @param[in]  domain_id value of a domain
- * @return     Returns true or false stating status notification support information
- *
- */
-bool is_status_notification_supported(int domain_id);
-
-/**
- * get_hmx_support_info API: query the DSP for HMX SUPPORT information
- *
- * @param[in]   domain_id value of a domain
- * @param[out]  capability capability value of the attribute queried.
- * @param[in]   attr value of the attribute to the queried.
- * @return      0 if query is successful.
- *              non-zero if error, return value points to the error.
- *
- */
-int get_hmx_support_info(int domain, uint32_t * capability, uint32_t attr);
-
-/**
- * get_hex_arch_ver API: query the Hexagon processor architecture version information
- *
- * @param[in]   domain_id value of a domain
- * @param[out]  Arch version (73, 75, ...)
- * @return      0 if query is successful.
- *              non-zero if error, return value points to the error.
- *
- */
-int get_hex_arch_ver(int domain, int * arch);
-
-/**
- * get_hvx_support_info API: query the DSP for HVX SUPPORT information
- *
- * @param[in]   domain_id value of a domain
- * @param[out]  capability capability value of the attribute queried.
- * @param[in]   attr value of the attribute to the queried.
- * @return      0 if query is successful.
- *              non-zero if error, return value points to the error.
- *
- */
-int get_hvx_support_info(int domain, uint32_t * capability, uint32_t attr);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif  //DSP_CAPABILITIES_UTILS_H

ggml/src/ggml-hexagon/libdl.h

@@ -0,0 +1,79 @@
+#pragma once
+
+#ifdef _WIN32
+#   define WIN32_LEAN_AND_MEAN
+#   ifndef NOMINMAX
+#       define NOMINMAX
+#   endif
+#   include <windows.h>
+#   include <winevt.h>
+#else
+#    include <dlfcn.h>
+#    include <unistd.h>
+#endif
+#include <filesystem>
+
+namespace fs = std::filesystem;
+
+#ifdef _WIN32
+
+using dl_handle = std::remove_pointer_t<HMODULE>;
+
+struct dl_handle_deleter {
+    void operator()(HMODULE handle) {
+        FreeLibrary(handle);
+    }
+};
+
+static inline dl_handle * dl_load_library(const fs::path & path) {
+    // suppress error dialogs for missing DLLs
+    DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+    SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+    HMODULE handle = LoadLibraryW(path.wstring().c_str());
+
+    SetErrorMode(old_mode);
+
+    return handle;
+}
+
+static inline void * dl_get_sym(dl_handle * handle, const char * name) {
+    DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+    SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+    void * p = (void *) GetProcAddress(handle, name);
+
+    SetErrorMode(old_mode);
+
+    return p;
+}
+
+static inline const char * dl_error() {
+    return "";
+}
+
+#else
+
+using dl_handle = void;
+
+struct dl_handle_deleter {
+    void operator()(void * handle) {
+        dlclose(handle);
+    }
+};
+
+static inline dl_handle * dl_load_library(const fs::path & path) {
+    dl_handle * handle = dlopen(path.string().c_str(), RTLD_NOW | RTLD_LOCAL);
+    return handle;
+}
+
+static inline void * dl_get_sym(dl_handle * handle, const char * name) {
+    return dlsym(handle, name);
+}
+
+static inline const char * dl_error() {
+    const char *rslt = dlerror();
+    return rslt != nullptr ? rslt : "";
+}
+
+#endif

ggml/src/ggml-hexagon/libggml-htp.inf

@@ -0,0 +1,38 @@
+[Version]
+Signature   = "$WINDOWS NT$"
+Class       = ComputeAccelerator
+ClassGuid   = {F01A9D53-3FF6-48D2-9F97-C8A7004BE10C}
+Provider    = %GGML%
+DriverVer   = 01/01/2026,1.0.0.0
+CatalogFile = libggml-htp.cat
+PnpLockDown = 1
+
+[DestinationDirs]
+Drivers_Dir = 6
+
+[SourceDisksNames]
+1 = %DiskId%
+
+[SourceDisksFiles]
+libggml-htp-v68.so = 1
+libggml-htp-v69.so = 1
+libggml-htp-v73.so = 1
+libggml-htp-v75.so = 1
+libggml-htp-v81.so = 1
+
+[ControlFlags]
+ExcludeFromSelect = *
+
+[DefaultInstall.NTarm64]
+CopyFiles=Drivers_Dir
+
+[Drivers_Dir]
+libggml-htp-v68.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v69.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v73.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v75.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v81.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+
+[Strings]
+GGML   = 'GGML'
+DiskId = 'GGML HTP library'

models/templates/upstage-Solar-Open-100B.jinja

@@ -0,0 +1,156 @@
+{#- ======== Template Parameters ========  #}
+{%- set add_generation_prompt = add_generation_prompt if add_generation_prompt is defined else true %}
+{%- set default_system_prompt = default_system_prompt if default_system_prompt is defined else true %}
+{%- set reasoning_effort = reasoning_effort if reasoning_effort is defined else "high" %}
+{%- set think_render_option = think_render_option if think_render_option is defined else "lastthink" %}
+
+{#- ======== System Block State ========  #}
+{%- set sys_ns = namespace(is_first_block=true) -%}
+
+{#- ======== Find last user message index ========  #}
+{%- set last_user_idx = namespace(value=-1) -%}
+{%- for message in messages -%}
+    {%- if message.role == 'user' -%}
+        {%- set last_user_idx.value = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- ======== System messages renderers ========  #}
+{%- macro render_system_message(user_system_messages) %}
+    {%- if default_system_prompt %}
+        {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+        {%- set sys_ns.is_first_block = false %}
+        {{- "## Provider System Prompt\n\nYou are Solar Open 100B, a large language model trained by Upstage AI, a Korean startup. Your knowledge cutoff is 2025-07. The current date is " + strftime_now("%Y-%m-%d") + "." }}
+    {%- endif -%}
+    {%- if user_system_messages %}
+        {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+        {%- set sys_ns.is_first_block = false %}
+        {{- "## System Prompt" }}
+        {%- for system_message in user_system_messages %}
+            {{- "\n\n" }}
+            {{- system_message }}
+        {%- endfor %}
+    {%- endif -%}
+{%- endmacro %}
+
+{%- macro render_tool_instruction(tools) %}
+    {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+    {%- set sys_ns.is_first_block = false %}
+    {{- "## Tools\n\n### Tool Call Instruction" }}
+    {{- "\nYou may invoke one or more tools to assist with the user's query. Available tools are provided in JSON Schema format: <|tools:begin|><|tool:begin|><tools-json-object><|tool:end|>...<|tools:end|>\n" }}
+    {{- "\n### Available Tools\n" }}
+    {{- "<|tools:begin|>" }}
+    {%- for tool in tools %}
+        {{- "<|tool:begin|>" }}
+        {{- tool.function | tojson }}
+        {{- "<|tool:end|>" }}
+    {%- endfor %}
+    {{- "<|tools:end|>\n" }}
+    {{- "\n### Tool Call Format\n" }}
+    {{- "For each tool call, return a JSON object with the following structure, enclosed within <|tool_call:begin|> and <|tool_call:end|> tags: \n<|tool_call:begin|><tool-call-id><|tool_call:name|><tool-name><|tool_call:args|><args-json-object><|tool_call:end|>\n" }}
+    {{- "- The <tool-call-id> must be a randomly generated string consisting of 10 lowercase letters (a-z) and/or digits (0-9) (e.g., a1b2c3d4e5)\n" }}
+    {{- "\n### Tool Response Format\n" }}
+    {{- "Each tool is responded by `tool` with the following structure:\n<|tool_response:id|><tool-call-id><|tool_response:name|><tool-name><|tool_response:result|><results><|tool_response:end|>\n" }}
+    {{- "- Ensure the <tool-call-id> matches the corresponding tool call" -}}
+{%- endmacro %}
+
+{%- macro render_json_response_format_instruction(response_format) %}
+    {%- if not sys_ns.is_first_block %}{{- "\n\n" }}{%- endif %}
+    {%- set sys_ns.is_first_block = false %}
+    {{- "## Output Format Constraint" }}
+    {{- "\n\nYour final response should follow the JSON schema: \n[Start of schema]" }}
+    {{- response_format }}
+    {{- "\n[End of schema]\nPlease ensure your answers adhere to this format and do not contain any unnecessary text." }}
+{%- endmacro %}
+
+{%- macro get_tool_name(messages, tool_call_id) %}
+    {%- for msg in messages -%}
+        {%- if msg.role == 'assistant' and msg.tool_calls -%}
+            {%- for tool_call in msg.tool_calls -%}
+                {%- if tool_call.id == tool_call_id -%}
+                    {{- tool_call.function.name }}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro %}
+
+{%- macro render_tool_arguments(tool_arguments) %}
+    {%- if tool_arguments is mapping -%}
+        {{- tool_arguments | tojson }}
+    {%- else -%}
+        {{- tool_arguments }}
+    {%- endif -%}
+{%- endmacro %}
+
+{#- ======== Render system message ========  #}
+{%- set ns = namespace(system_messages=[]) -%}
+{%- for message in messages -%}
+    {%- if message.role == 'system' -%}
+        {%- set ns.system_messages = ns.system_messages + [message.content] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if ns.system_messages or default_system_prompt or tools or response_format -%}
+    {{- "<|begin|>system<|content|>" }}
+        {{- render_system_message(ns.system_messages) }}
+        {%- if tools -%}
+            {{- render_tool_instruction(tools) }}
+        {%- endif %}
+        {%- if response_format -%}
+            {{- render_json_response_format_instruction(response_format) }}
+        {%- endif %}
+    {{- "<|end|>" }}
+{%- endif -%}
+
+{#- ======== Render main messages ========  #}
+{%- for message in messages -%}
+    {%- if message.role == 'user' -%}
+         {{- "<|begin|>user<|content|>" + message.content + "<|end|>" }}
+    {%- elif message.role == 'tool' -%}
+        {%- set prev_is_tool = loop.index0 > 0 and messages[loop.index0 - 1].role == 'tool' -%}
+        {%- set next_is_tool = loop.index0 < (messages | length - 1) and messages[loop.index0 + 1].role == 'tool' -%}
+        {%- if not prev_is_tool -%}
+            {{- "<|begin|>tool<|tool_response|>" }}
+        {%- endif -%}
+        {{- "<|tool_response:begin|>" + message.tool_call_id + "<|tool_response:name|>" }}
+        {{- get_tool_name(messages, message.tool_call_id) }}
+        {{- "<|tool_response:result|>" }}
+        {{- message.content }}
+        {{- "<|tool_response:end|>" }}
+        {%- if not next_is_tool -%}
+            {{- "<|end|>" }}
+        {%- endif -%}
+    {%- elif message.role == 'assistant' -%}
+        {#- ======== Assistant Thinking ========  #}
+        {%- if think_render_option == "all" -%}
+            {%- if message.reasoning -%}
+                {{- "<|begin|>assistant<|think|>" + message.reasoning + "<|end|>" }}
+            {%- endif -%}
+        {%- elif think_render_option == "lastthink" -%}
+            {%- if message.reasoning and loop.index0 > last_user_idx.value -%}
+                {{- "<|begin|>assistant<|think|>" + message.reasoning + "<|end|>" }}
+            {%- endif -%}
+        {%- endif -%}
+
+        {#- ======== Assistant Messages ========  #}
+        {%- if message.tool_calls -%}
+            {{- "<|begin|>assistant<|tool_calls|>" }}
+            {%- for tool_call in message.tool_calls -%}
+                {{- "<|tool_call:begin|>" + tool_call.id +"<|tool_call:name|>" + tool_call.function.name + "<|tool_call:args|>" }}
+                {{- render_tool_arguments(tool_call.function.arguments) }}
+                {{- "<|tool_call:end|>" }}
+            {%- endfor -%}
+            {{- "<|calls|>" }}
+        {%- else -%}
+            {{- "<|begin|>assistant<|content|>" + message.content + "<|end|>" }}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if reasoning_effort in ["low", "minimal"] -%}
+        {{- "<|begin|>assistant<|think|><|end|>" }}
+    {%- endif -%}
+    {{- "<|begin|>assistant" }}
+{%- endif -%}

scripts/snapdragon/windows/run-bench.ps1

@@ -0,0 +1,40 @@
+
+#!/usr/bin/env pwsh
+
+# Basedir on device
+$basedir=".\pkg-snapdragon"
+
+$cli_opts=$args
+
+$model="Llama-3.2-3B-Instruct-Q4_0.gguf"
+if ($null -ne $env:M) {
+    $model=$env:M
+}
+
+$device="HTP0"
+if ($null -ne $env:D) {
+    $device=$env:D
+}
+
+if ($null -ne $env:V) {
+    $env:GGML_HEXAGON_VERBOSE=$env:V
+}
+
+if ($null -ne $env:OPMASK) {
+    $env:GGML_HEXAGON_OPMASK=$env:OPMASK
+}
+
+if ($null -ne $env:NHVX) {
+    $env:GGML_HEXAGON_NHVX=$env:NHVX
+}
+
+if ($null -ne $env:NDEV) {
+    $env:GGML_HEXAGON_NDEV=$env:NDEV
+}
+
+$env:ADSP_LIBRARY_PATH="$basedir\lib"
+
+& "$basedir\bin\llama-bench.exe" `
+    --mmap 0 -m $basedir\..\..\gguf\$model `
+    --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 `
+    --batch-size 128 -ngl 99 --device $device $cli_opts

scripts/snapdragon/windows/run-cli.ps1

@@ -0,0 +1,53 @@
+
+#!/usr/bin/env pwsh
+
+# Basedir on device
+$basedir=".\pkg-snapdragon"
+
+$cli_opts=$args
+
+$model="Llama-3.2-3B-Instruct-Q4_0.gguf"
+if ($null -ne $env:M) {
+    $model=$env:M
+}
+
+$device="HTP0"
+if ($null -ne $env:D) {
+    $device=$env:D
+}
+
+if ($null -ne $env:V) {
+    $env:GGML_HEXAGON_VERBOSE=$env:V
+}
+
+if ($null -ne $env:E) {
+    $env:GGML_HEXAGON_EXPERIMENTAL=$env:E
+}
+
+if ($null -ne $env:SCHED) {
+    $env:GGML_SCHED_DEBUG=$env:SCHED; $cli_opts="$cli_opts -v"
+}
+
+if ($null -ne $env:PROF) {
+    $env:GGML_HEXAGON_PROFILE=$env:PROF; $env:GGML_HEXAGON_OPSYNC=1
+}
+
+if ($null -ne $env:OPMASK) {
+    $env:GGML_HEXAGON_OPMASK=$env:OPMASK
+}
+
+if ($null -ne $env:NHVX) {
+    $env:GGML_HEXAGON_NHVX=$env:NHVX
+}
+
+if ($null -ne $env:NDEV) {
+    $env:GGML_HEXAGON_NDEV=$env:NDEV
+}
+
+$env:ADSP_LIBRARY_PATH="$basedir\lib"
+
+& "$basedir\bin\llama-completion.exe" `
+    --no-mmap -no-cnv -m $basedir\..\..\gguf\$model `
+    --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 `
+    --ctx-size 8192 --batch-size 128 -ctk q8_0 -ctv q8_0 -fa on `
+    -ngl 99 --device $device $cli_opts

scripts/snapdragon/windows/run-tool.ps1

@@ -0,0 +1,56 @@
+
+#!/usr/bin/env pwsh
+
+# Basedir on device
+$basedir=".\pkg-snapdragon"
+
+if ($args.Count -eq 0) {
+    Write-Host "No arguments provided.Expected the tool and argument to run."
+    exit -1
+}
+
+$tool=$args[0]
+$cli_opts=@()
+
+if ($args.Count -gt 1) {
+    $cli_opts=$args[1..($args.Count - 1)]
+    $remainingArgs = $args[1..($args.Count - 1)]
+}
+
+$device="HTP0"
+if ($null -ne $env:D) {
+    $device=$env:D
+}
+
+if ($null -ne $env:V) {
+    $env:GGML_HEXAGON_VERBOSE=$env:V
+}
+
+if ($null -ne $env:E) {
+    $env:GGML_HEXAGON_EXPERIMENTAL=$env:E
+}
+
+if ($null -ne $env:SCHED) {
+    $env:GGML_SCHED_DEBUG=$env:SCHED; $cli_opts="$cli_opts -v"
+}
+
+if ($null -ne $env:PROF) {
+    $env:GGML_HEXAGON_PROFILE=$env:PROF; $env:GGML_HEXAGON_OPSYNC=1
+}
+
+if ($null -ne $env:OPMASK) {
+    $env:GGML_HEXAGON_OPMASK=$env:OPMASK
+}
+
+if ($null -ne $env:NHVX) {
+    $env:GGML_HEXAGON_NHVX=$env:NHVX
+}
+
+if ($null -ne $env:NDEV) {
+    $env:GGML_HEXAGON_NDEV=$env:NDEV
+}
+
+$env:ADSP_LIBRARY_PATH="$basedir\lib"
+
+& "$basedir\bin\$tool" `
+    $cli_opts

scripts/snapdragon/windows/setup-build.ps1

@@ -0,0 +1,105 @@
+# Requires Run as Administrator is NOT strictly necessary for User-scope env vars,
+# but recommended for creating directories in C:\ root if permissions are restricted.
+
+$ErrorActionPreference = "Stop"
+
+# --- Configuration ---
+$BaseDir = "C:\Qualcomm"
+
+# SDK 1: Hexagon
+$HexagonUrl     = "https://github.com/snapdragon-toolchain/hexagon-sdk/releases/download/v6.4.0.2/hexagon-sdk-v6.4.0.2-arm64-wos.tar.xz"
+$HexagonParent  = Join-Path $BaseDir "Hexagon_SDK"
+$HexagonSdkVersion   = "6.4.0.2"
+$HexagonToolsVersion = "19.0.04"
+$HexagonSdkTarget    = Join-Path $HexagonParent $HexagonSdkVersion
+$HexagonToolsTarget  = Join-Path $HexagonSdkTarget "\tools\HEXAGON_Tools\$HexagonToolsVersion"
+
+# SDK 2: OpenCL
+$OpenCLUrl      = "https://github.com/snapdragon-toolchain/opencl-sdk/releases/download/v2.3.2/adreno-opencl-sdk-v2.3.2-arm64-wos.tar.xz"
+$OpenCLParent   = Join-Path $BaseDir "OpenCL_SDK"
+$OpenCLVersion  = "2.3.2"
+$OpenCLTarget   = Join-Path $OpenCLParent $OpenCLVersion
+
+# --- Helper Function ---
+function Install-QualcommSDK {
+    param (
+        [string]$Url,
+        [string]$ParentDir,
+        [string]$TargetDir,
+        [string]$Name
+    )
+
+    # 1. Create Parent Directory
+    if (-not (Test-Path -Path $ParentDir)) {
+        Write-Host "Creating directory: $ParentDir" -ForegroundColor Cyan
+        New-Item -Path $ParentDir -ItemType Directory -Force | Out-Null
+    }
+
+    # 2. Check for Specific Version Directory
+    if (Test-Path -Path $TargetDir) {
+        Write-Host "$Name ($TargetDir) already exists. Skipping download." -ForegroundColor Green
+    }
+    else {
+        Write-Host "$Name not found. preparing to download..." -ForegroundColor Yellow
+
+        # Create the target directory to extract into
+        New-Item -Path $TargetDir -ItemType Directory -Force | Out-Null
+
+        # Define temporary archive path
+        $TempFile = Join-Path $ParentDir "temp_sdk.tar.xz"
+
+        try {
+            # Download
+            Write-Host "Downloading from: $Url"
+            Invoke-WebRequest -Uri $Url -OutFile $TempFile
+
+            # Untar
+            # Note: We assume Windows includes tar.exe (Win 10 build 17063+)
+            Write-Host "Extracting archive to $TargetDir..."
+
+            # We use -C to extract contents INTO the target directory created above
+            tar -xJvf $TempFile -C $TargetDir\..
+
+            Write-Host "Extraction complete." -ForegroundColor Green
+        }
+        catch {
+            Write-Error "Failed to download or extract $Name. Error: $_"
+            # Cleanup target dir if failed so script tries again next time
+            Remove-Item -Path $TargetDir -Recurse -Force -ErrorAction SilentlyContinue
+        }
+        finally {
+            # Cleanup Archive
+            if (Test-Path $TempFile) { Remove-Item $TempFile -Force }
+        }
+    }
+}
+
+# --- Execution ---
+
+# 1. Ensure Base C:\Qualcomm exists
+if (-not (Test-Path $BaseDir)) {
+    New-Item -Path $BaseDir -ItemType Directory -Force | Out-Null
+}
+
+# 2. Run Install Logic
+Install-QualcommSDK -Url $HexagonUrl -ParentDir $HexagonParent -TargetDir $HexagonSdkTarget -Name "Hexagon SDK"
+Install-QualcommSDK -Url $OpenCLUrl -ParentDir $OpenCLParent -TargetDir $OpenCLTarget -Name "OpenCL SDK"
+
+# --- Environment Variables ---
+
+Write-Host "`nSetting Environment Variables..." -ForegroundColor Cyan
+
+# Set OPENCL_SDK_ROOT
+[System.Environment]::SetEnvironmentVariable('OPENCL_SDK_ROOT', $OpenCLTarget, [System.EnvironmentVariableTarget]::User)
+$env:OPENCL_SDK_ROOT = $OpenCLTarget # Set for current session as well
+Write-Host "OPENCL_SDK_ROOT set to:  $OpenCLTarget"
+
+# Set HEXAGON_SDK_ROOT
+[System.Environment]::SetEnvironmentVariable('HEXAGON_SDK_ROOT', $HexagonSdkTarget, [System.EnvironmentVariableTarget]::User)
+$env:HEXAGON_SDK_ROOT = $HexagonSdkTarget # Set for current session as well
+Write-Host "HEXAGON_SDK_ROOT set to: $HexagonSdkTarget"
+
+# Set HEXAGON_SDK_ROOT
+[System.Environment]::SetEnvironmentVariable('HEXAGON_TOOLS_ROOT', $HexagonToolsTarget, [System.EnvironmentVariableTarget]::User)
+$env:HEXAGON_TOOLS_ROOT = $HexagonToolsTarget # Set for current session as well
+Write-Host "HEXAGON_TOOLS_ROOT set to: $HexagonToolsTarget"

src/llama-graph.cpp

@@ -1630,11 +1630,6 @@ ggml_tensor * llm_graph_context::build_attn_mha(
                                   hparams.attn_soft_cap ? hparams.f_attn_logit_softcapping : 0.0f);
         cb(cur, LLAMA_TENSOR_NAME_FATTN, il);
 
-        if (!cparams.offload_kqv) {
-            // all nodes between the KV store and the attention output are run on the CPU
-            ggml_backend_sched_set_tensor_backend(sched, cur, backend_cpu);
-        }
-
         ggml_flash_attn_ext_add_sinks(cur, sinks);
         ggml_flash_attn_ext_set_prec (cur, GGML_PREC_F32);
 

tests/test-chat.cpp

@@ -592,7 +592,7 @@ static void test_peg_parser(common_chat_templates * tmpls, const std::function<v
             }
             if (diff.tool_call_index != std::string::npos) {
                 if (!diff.tool_call_delta.name.empty()) {
-                    msg_accum.tool_calls.push_back({diff.tool_call_delta.name, "", ""});
+                    msg_accum.tool_calls.push_back({diff.tool_call_delta.name, "", diff.tool_call_delta.id});
                 }
                 if (!diff.tool_call_delta.arguments.empty()) {
                     msg_accum.tool_calls.back().arguments += diff.tool_call_delta.arguments;
@@ -3799,6 +3799,134 @@ static void test_template_output_peg_parsers() {
         });
     }
 
+    {
+        // Solar-Open-100B
+        auto tmpls = read_templates("models/templates/upstage-Solar-Open-100B.jinja");
+
+        // Test basic message
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|content|>Hello, world!\nWhat's up?";
+            t.expect = message_assist;
+        });
+
+        // Test basic message and reasoning
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|think|>I'm\nthinking<|end|><|begin|>assistant<|content|>Hello, world!\nWhat's up?";
+            t.expect = message_assist_thoughts;
+        });
+
+        // Test basic message and reasoning_effort = low
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|content|>Hello, world!\nWhat's up?";
+            t.params.chat_template_kwargs["reasoning_effort"] = "\"low\"";
+            t.expect = message_assist;
+        });
+
+        // Test tool call
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|tool_calls|>"
+                      "<|tool_call:begin|>123456789"
+                      "<|tool_call:name|>special_function"
+                      "<|tool_call:args|>{\"arg1\":1}"
+                      "<|tool_call:end|>";
+
+            t.params.chat_template_kwargs["reasoning_effort"] = "\"low\"";
+            t.params.tools = {special_function_tool};
+            t.expect = message_assist_call_id;
+        });
+
+        // Test tool call with reasoning
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|think|>I'm\nthinking<|end|>"
+                      "<|begin|>assistant<|tool_calls|>"
+                      "<|tool_call:begin|>0"
+                      "<|tool_call:name|>special_function"
+                      "<|tool_call:args|>{\"arg1\":1}"
+                      "<|tool_call:end|>";
+
+            t.params.tools = {special_function_tool};
+            t.expect = message_assist_thoughts_call_idx;
+        });
+
+        // Test tool call with reasoning and tool_choice = required
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|think|>I'm\nthinking<|end|>"
+                      "<|begin|>assistant<|tool_calls|>"
+                      "<|tool_call:begin|>0"
+                      "<|tool_call:name|>special_function"
+                      "<|tool_call:args|>{\"arg1\":1}"
+                      "<|tool_call:end|>";
+
+            t.params.tools = {special_function_tool};
+            t.params.tool_choice = COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+            t.expect = message_assist_thoughts_call_idx;
+        });
+
+        // Test tool call without reasoning and tool_choice = required
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|tool_calls|>"
+                      "<|tool_call:begin|>0"
+                      "<|tool_call:name|>special_function"
+                      "<|tool_call:args|>{\"arg1\":1}"
+                      "<|tool_call:end|>";
+
+            t.params.tools = {special_function_tool};
+            t.params.tool_choice = COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+            t.params.chat_template_kwargs["reasoning_effort"] = "\"low\"";
+            t.expect = message_assist_call_idx;
+        });
+
+        // Test parallel tool calls
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|think|>I'm\nthinking<|end|>"
+                      "<|begin|>assistant<|tool_calls|>"
+                      "<|tool_call:begin|>0"
+                      "<|tool_call:name|>special_function"
+                      "<|tool_call:args|>{\"arg1\":1}"
+                      "<|tool_call:end|>"
+                      "<|tool_call:begin|>1"
+                      "<|tool_call:name|>special_function_with_opt"
+                      "<|tool_call:args|>{\"arg1\": 1, \"arg2\": 2}"
+                      "<|tool_call:end|>";
+
+            t.params.parallel_tool_calls = true;
+            t.params.tools = {special_function_tool, special_function_tool_with_optional_param};
+
+            t.expect.reasoning_content = "I'm\nthinking";
+            t.expect.tool_calls = {{
+                /* .name = */      "special_function",
+                /* .arguments = */ R"({"arg1": 1})",
+                /* .id = */        "0",
+            }, {
+                /* .name = */      "special_function_with_opt",
+                /* .arguments = */ R"({"arg1": 1, "arg2": 2})",
+                /* .id = */        "1",
+            }};
+        });
+
+        // Test response format
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|think|>I need to output the invoice details in JSON<|end|>"
+                      "<|begin|>assistant<|content|>"
+                      R"({"amount": 123.45, "date": "2025-12-03"})";
+
+            t.params.json_schema = invoice_schema;
+
+            t.expect.reasoning_content = "I need to output the invoice details in JSON";
+            t.expect.content =R"({"amount": 123.45, "date": "2025-12-03"})";
+        });
+
+        // Test response format no reasoning
+        test_peg_parser(tmpls.get(), [&](auto & t) {
+            t.input = "<|content|>"
+                      R"({"amount": 123.45, "date": "2025-12-03"})";
+
+            t.params.chat_template_kwargs["reasoning_effort"] = "\"low\"";
+            t.params.json_schema = invoice_schema;
+
+            t.expect.content =R"({"amount": 123.45, "date": "2025-12-03"})";
+        });
+    }
 }
 
 static void test_msg_diffs_compute() {

tools/server/webui/package-lock.json

@@ -61,7 +61,7 @@
 				"remark-math": "^6.0.0",
 				"sass": "^1.93.3",
 				"storybook": "^10.0.7",
-				"svelte": "^5.0.0",
+				"svelte": "^5.38.2",
 				"svelte-check": "^4.0.0",
 				"tailwind-merge": "^3.3.1",
 				"tailwind-variants": "^3.2.2",
@@ -88,6 +88,7 @@
 			"version": "2.3.0",
 			"resolved": "https://registry.npmjs.org/@ampproject/remapping/-/remapping-2.3.0.tgz",
 			"integrity": "sha512-30iZtAPgz+LTIYoeivqYo853f02jBYSd5uGnGpkFV0M3xOt9aN73erkgYAmZU43x4VfqcnLxW9Kpg3R5LC4YYw==",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@jridgewell/gen-mapping": "^0.3.5",
@@ -867,6 +868,7 @@
 			"integrity": "sha512-oJrXtQiAXLvT9clCf1K4kxp3eKsQhIaZqxEyowkBcsvZDdZkbWrVmnGknxs5flTD0VGsxrxKgBCZty1EzoiMzA==",
 			"dev": true,
 			"license": "Apache-2.0",
+			"peer": true,
 			"dependencies": {
 				"@swc/helpers": "^0.5.0"
 			}
@@ -898,7 +900,6 @@
 			"version": "2.3.5",
 			"resolved": "https://registry.npmjs.org/@jridgewell/remapping/-/remapping-2.3.5.tgz",
 			"integrity": "sha512-LI9u/+laYG4Ds1TDKSJW2YPrIlcVYOwi2fUC6xB43lueCjgxV4lffOCZCtYFiH6TNOX+tQKXx97T4IKHbhyHEQ==",
-			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"@jridgewell/gen-mapping": "^0.3.5",
@@ -2031,6 +2032,7 @@
 			"integrity": "sha512-rO+YQhHucy47Vh67z318pALmd6x+K1Kj30Fb4a6oOEw4xn4zCo9KTmkMWs24c4oduEXD/eJu3badlRmsVXzyfA==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"ts-dedent": "^2.0.0",
 				"type-fest": "~2.19"
@@ -2114,6 +2116,7 @@
 			"integrity": "sha512-Vp3zX/qlwerQmHMP6x0Ry1oY7eKKRcOWGc2P59srOp4zcqyn+etJyQpELgOi4+ZSUgteX8Y387NuwruLgGXLUQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@standard-schema/spec": "^1.0.0",
 				"@sveltejs/acorn-typescript": "^1.0.5",
@@ -2153,6 +2156,7 @@
 			"integrity": "sha512-YZs/OSKOQAQCnJvM/P+F1URotNnYNeU3P2s4oIpzm1uFaqUEqRxUB0g5ejMjEb5Gjb9/PiBI5Ktrq4rUUF8UVQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@sveltejs/vite-plugin-svelte-inspector": "^5.0.0",
 				"debug": "^4.4.1",
@@ -2568,6 +2572,7 @@
 			"integrity": "sha512-pemlzrSESWbdAloYml3bAJMEfNh1Z7EduzqPKprCH5S341frlpYnUEW0H72dLxa6IsYr+mPno20GiSm+h9dEdQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@babel/code-frame": "^7.10.4",
 				"@babel/runtime": "^7.12.5",
@@ -2735,6 +2740,7 @@
 			"integrity": "sha512-bJFoMATwIGaxxx8VJPeM8TonI8t579oRvgAuT8zFugJsJZgzqv0Fu8Mhp68iecjzG7cnN3mO2dJQ5uUM2EFrgQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"undici-types": "~6.21.0"
 			}
@@ -2802,6 +2808,7 @@
 			"integrity": "sha512-kVIaQE9vrN9RLCQMQ3iyRlVJpTiDUY6woHGb30JDkfJErqrQEmtdWH3gV0PBAfGZgQXoqzXOO0T3K6ioApbbAA==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@typescript-eslint/scope-manager": "8.37.0",
 				"@typescript-eslint/types": "8.37.0",
@@ -3026,6 +3033,7 @@
 			"integrity": "sha512-tJxiPrWmzH8a+w9nLKlQMzAKX/7VjFs50MWgcAj7p9XQ7AQ9/35fByFYptgPELyLw+0aixTnC4pUWV+APcZ/kw==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@testing-library/dom": "^10.4.0",
 				"@testing-library/user-event": "^14.6.1",
@@ -3129,6 +3137,7 @@
 			"integrity": "sha512-oukfKT9Mk41LreEW09vt45f8wx7DordoWUZMYdY/cyAk7w5TWkTRCNZYF7sX7n2wB7jyGAl74OxgwhPgKaqDMQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@vitest/utils": "3.2.4",
 				"pathe": "^2.0.3",
@@ -3186,6 +3195,7 @@
 			"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
 			"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
 			"license": "MIT",
+			"peer": true,
 			"bin": {
 				"acorn": "bin/acorn"
 			},
@@ -3738,8 +3748,7 @@
 			"resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz",
 			"integrity": "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw==",
 			"dev": true,
-			"license": "MIT",
-			"peer": true
+			"license": "MIT"
 		},
 		"node_modules/debug": {
 			"version": "4.4.1",
@@ -3840,10 +3849,9 @@
 			}
 		},
 		"node_modules/devalue": {
-			"version": "5.3.2",
-			"resolved": "https://registry.npmjs.org/devalue/-/devalue-5.3.2.tgz",
-			"integrity": "sha512-UDsjUbpQn9kvm68slnrs+mfxwFkIflOhkanmyabZ8zOYk8SMEIbJ3TK+88g70hSIeytu4y18f0z/hYHMTrXIWw==",
-			"dev": true,
+			"version": "5.6.2",
+			"resolved": "https://registry.npmjs.org/devalue/-/devalue-5.6.2.tgz",
+			"integrity": "sha512-nPRkjWzzDQlsejL1WVifk5rvcFi/y1onBRxjaFMjZeR9mFpqu2gmAZ9xUB9/IEanEP/vBtGeGganC/GO1fmufg==",
 			"license": "MIT"
 		},
 		"node_modules/devlop": {
@@ -3973,6 +3981,7 @@
 			"dev": true,
 			"hasInstallScript": true,
 			"license": "MIT",
+			"peer": true,
 			"bin": {
 				"esbuild": "bin/esbuild"
 			},
@@ -4027,6 +4036,7 @@
 			"integrity": "sha512-QldCVh/ztyKJJZLr4jXNUByx3gR+TDYZCRXEktiZoUR3PGy4qCmSbkxcIle8GEwGpb5JBZazlaJ/CxLidXdEbQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@eslint-community/eslint-utils": "^4.2.0",
 				"@eslint-community/regexpp": "^4.12.1",
@@ -6939,6 +6949,7 @@
 				}
 			],
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"nanoid": "^3.3.11",
 				"picocolors": "^1.1.1",
@@ -7072,6 +7083,7 @@
 			"integrity": "sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"bin": {
 				"prettier": "bin/prettier.cjs"
 			},
@@ -7088,6 +7100,7 @@
 			"integrity": "sha512-pn1ra/0mPObzqoIQn/vUTR3ZZI6UuZ0sHqMK5x2jMLGrs53h0sXhkVuDcrlssHwIMk7FYrMjHBPoUSyyEEDlBQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"peerDependencies": {
 				"prettier": "^3.0.0",
 				"svelte": "^3.2.0 || ^4.0.0-next.0 || ^5.0.0-next.0"
@@ -7312,6 +7325,7 @@
 			"integrity": "sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"engines": {
 				"node": ">=0.10.0"
 			}
@@ -7322,6 +7336,7 @@
 			"integrity": "sha512-Xs1hdnE+DyKgeHJeJznQmYMIBG3TKIHJJT95Q58nHLSrElKlGQqDTR2HQ9fx5CN/Gk6Vh/kupBTDLU11/nDk/g==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"scheduler": "^0.26.0"
 			},
@@ -7598,6 +7613,7 @@
 			"integrity": "sha512-4iya7Jb76fVpQyLoiVpzUrsjQ12r3dM7fIVz+4NwoYvZOShknRmiv+iu9CClZml5ZLGb0XMcYLutK6w9tgxHDw==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@types/estree": "1.0.8"
 			},
@@ -7704,6 +7720,7 @@
 			"integrity": "sha512-elOcIZRTM76dvxNAjqYrucTSI0teAF/L2Lv0s6f6b7FOwcwIuA357bIE871580AjHJuSvLIRUosgV+lIWx6Rgg==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"chokidar": "^4.0.0",
 				"immutable": "^5.0.2",
@@ -7938,6 +7955,7 @@
 			"integrity": "sha512-7smAu0o+kdm378Q2uIddk32pn0UdIbrtTVU+rXRVtTVTCrK/P2cCui2y4JH+Bl3NgEq1bbBQpCAF/HKrDjk2Qw==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@storybook/global": "^5.0.0",
 				"@storybook/icons": "^1.6.0",
@@ -8079,12 +8097,13 @@
 			}
 		},
 		"node_modules/svelte": {
-			"version": "5.36.12",
-			"resolved": "https://registry.npmjs.org/svelte/-/svelte-5.36.12.tgz",
-			"integrity": "sha512-c3mWT+b0yBLl3gPGSHiy4pdSQCsPNTjLC0tVoOhrGJ6PPfCzD/RQpAmAfJtQZ304CAae2ph+L3C4aqds3R3seQ==",
+			"version": "5.48.3",
+			"resolved": "https://registry.npmjs.org/svelte/-/svelte-5.48.3.tgz",
+			"integrity": "sha512-w7QZ398cdNherTdiQ/v3SYLLGOO4948Jgjh04PYqtTYVohmBvbmFwLmo7pp8gp4/1tceRWfSTjHgjtfpCVNJmQ==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
-				"@ampproject/remapping": "^2.3.0",
+				"@jridgewell/remapping": "^2.3.4",
 				"@jridgewell/sourcemap-codec": "^1.5.0",
 				"@sveltejs/acorn-typescript": "^1.0.5",
 				"@types/estree": "^1.0.5",
@@ -8092,8 +8111,9 @@
 				"aria-query": "^5.3.1",
 				"axobject-query": "^4.1.0",
 				"clsx": "^2.1.1",
+				"devalue": "^5.6.2",
 				"esm-env": "^1.2.1",
-				"esrap": "^2.1.0",
+				"esrap": "^2.2.1",
 				"is-reference": "^3.0.3",
 				"locate-character": "^3.0.0",
 				"magic-string": "^0.30.11",
@@ -8281,9 +8301,9 @@
 			}
 		},
 		"node_modules/svelte/node_modules/esrap": {
-			"version": "2.1.0",
-			"resolved": "https://registry.npmjs.org/esrap/-/esrap-2.1.0.tgz",
-			"integrity": "sha512-yzmPNpl7TBbMRC5Lj2JlJZNPml0tzqoqP5B1JXycNUwtqma9AKCO0M2wHrdgsHcy1WRW7S9rJknAMtByg3usgA==",
+			"version": "2.2.2",
+			"resolved": "https://registry.npmjs.org/esrap/-/esrap-2.2.2.tgz",
+			"integrity": "sha512-zA6497ha+qKvoWIK+WM9NAh5ni17sKZKhbS5B3PoYbBvaYHZWoS33zmFybmyqpn07RLUxSmn+RCls2/XF+d0oQ==",
 			"license": "MIT",
 			"dependencies": {
 				"@jridgewell/sourcemap-codec": "^1.4.15"
@@ -8326,6 +8346,7 @@
 			"integrity": "sha512-gBXpgUm/3rp1lMZZrM/w7D8GKqshif0zAymAhbCyIt8KMe+0v9DQ7cdYLR4FHH/cKpdTXb+A/tKKU3eolfsI+g==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"funding": {
 				"type": "github",
 				"url": "https://github.com/sponsors/dcastil"
@@ -8356,7 +8377,8 @@
 			"resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.11.tgz",
 			"integrity": "sha512-2E9TBm6MDD/xKYe+dvJZAmg3yxIEDNRc0jwlNyDg/4Fil2QcSLjFKGVff0lAf1jjeaArlG/M75Ey/EYr/OJtBA==",
 			"dev": true,
-			"license": "MIT"
+			"license": "MIT",
+			"peer": true
 		},
 		"node_modules/tapable": {
 			"version": "2.2.2",
@@ -8569,6 +8591,7 @@
 			"integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
 			"dev": true,
 			"license": "Apache-2.0",
+			"peer": true,
 			"bin": {
 				"tsc": "bin/tsc",
 				"tsserver": "bin/tsserver"
@@ -8934,6 +8957,7 @@
 			"integrity": "sha512-BxAKBWmIbrDgrokdGZH1IgkIk/5mMHDreLDmCJ0qpyJaAteP8NvMhkwr/ZCQNqNH97bw/dANTE9PDzqwJghfMQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"esbuild": "^0.25.0",
 				"fdir": "^6.5.0",
@@ -9094,6 +9118,7 @@
 			"integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@types/chai": "^5.2.2",
 				"@vitest/expect": "3.2.4",

tools/server/webui/package.json

@@ -62,7 +62,7 @@
 		"remark-math": "^6.0.0",
 		"sass": "^1.93.3",
 		"storybook": "^10.0.7",
-		"svelte": "^5.0.0",
+		"svelte": "^5.38.2",
 		"svelte-check": "^4.0.0",
 		"tailwind-merge": "^3.3.1",
 		"tailwind-variants": "^3.2.2",