speculative-simple : free batch on exit (#17985)

* model-conversion : use CONVERTED_MODEL value for converted model [no ci]

This commit updates the model verification scripts to use the
CONVERTED_MODEL environment variable instead of using the MODEL_PATH
(the original model path) as the basis for the converted model file
name.

The motivation for this that currently if the converted model file name
differs from the original model directory/name the verification scripts
will look for the wrong .bin files that were generating when running the
models.
For example, the following steps were not possible:
```console
(venv) $ huggingface-cli download google/gemma-3-270m-it --local-dir ggml-org/gemma-3-270m
(venv) $ python3 convert_hf_to_gguf.py ggml-org/gemma-3-270m --outfile test-bf16.gguf --outtype bf16
(venv) $ cd examples/model-conversion/
(venv) $ export MODEL_PATH=../../ggml-org/gemma-3-270m
(venv) $ export CONVERTED_MODEL=../../test-bf16.gguf
(venv) $ make causal-verify-logits
...
Data saved to data/llamacpp-test-bf16.bin
Data saved to data/llamacpp-test-bf16.txt
Error: llama.cpp logits file not found: data/llamacpp-gemma-3-270m.bin
Please run scripts/run-converted-model.sh first to generate this file.
make: *** [Makefile:62: causal-verify-logits] Error 1
```

With the changes in this commit, the above steps will now work as
expected.

common/arg.cpp

@@ -504,7 +504,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
 
     // model is required (except for server)
     // TODO @ngxson : maybe show a list of available models in CLI in this case
-    if (params.model.path.empty() && ctx_arg.ex != LLAMA_EXAMPLE_SERVER && !params.usage) {
+    if (params.model.path.empty() && ctx_arg.ex != LLAMA_EXAMPLE_SERVER && !params.usage && !params.completion) {
         throw std::invalid_argument("error: --model is required\n");
     }
 
@@ -639,6 +639,7 @@ static void common_params_print_completion(common_params_context & ctx_arg) {
         "llama-batched-bench",
         "llama-bench",
         "llama-cli",
+        "llama-completion",
         "llama-convert-llama2c-to-ggml",
         "llama-cvector-generator",
         "llama-embedding",

examples/model-conversion/scripts/causal/compare-logits.py

@@ -1,10 +1,13 @@
 #!/usr/bin/env python3
 
-import numpy as np
 import sys
-import os
+import numpy as np
 from pathlib import Path
 
+# Add utils directory to path for direct script execution
+sys.path.insert(0, str(Path(__file__).parent.parent / "utils"))
+from common import get_model_name_from_env_path  # type: ignore[import-not-found]
+
 def quick_logits_check(pytorch_file, llamacpp_file):
     """Lightweight sanity check before NMSE"""
 
@@ -35,20 +38,13 @@ def quick_logits_check(pytorch_file, llamacpp_file):
     return True
 
 def main():
-    model_path = os.getenv('MODEL_PATH')
-    if not model_path:
-        print("Error: MODEL_PATH environment variable not set")
-        sys.exit(1)
-
-    if not os.path.exists(model_path):
-        print(f"Error: Model file not found: {model_path}")
-        sys.exit(1)
-
-    model_name = os.path.basename(model_path)
+    model_name = get_model_name_from_env_path('MODEL_PATH')
     data_dir = Path("data")
-
     pytorch_file = data_dir / f"pytorch-{model_name}.bin"
-    llamacpp_file = data_dir / f"llamacpp-{model_name}.bin"
+
+    llamacpp_model_name = get_model_name_from_env_path('CONVERTED_MODEL')
+    print(f"Using converted model: {llamacpp_model_name}")
+    llamacpp_file = data_dir / f"llamacpp-{llamacpp_model_name}.bin"
 
     if not pytorch_file.exists():
         print(f"Error: PyTorch logits file not found: {pytorch_file}")

examples/model-conversion/scripts/utils/check-nmse.py

@@ -5,6 +5,7 @@ import sys
 import os
 import argparse
 from pathlib import Path
+from common import get_model_name_from_env_path  # type: ignore[import-not-found]
 
 def calculate_nmse(reference, test):
     mse = np.mean((test - reference) ** 2)
@@ -67,11 +68,13 @@ def main():
     parser.add_argument('-m', '--model-path', required=True,  help='Path to the model directory')
     args = parser.parse_args()
 
-    model_name = os.path.basename(args.model_path)
+    model_name = get_model_name_from_env_path('MODEL_PATH')
     data_dir = Path("data")
 
     pytorch_file = data_dir / f"pytorch-{model_name}.bin"
-    llamacpp_file = data_dir / f"llamacpp-{model_name}.bin"
+
+    llamacpp_model_name = get_model_name_from_env_path('CONVERTED_MODEL')
+    llamacpp_file = data_dir / f"llamacpp-{llamacpp_model_name}.bin"
 
     print(f"Model name: {model_name}")
     print(f"PyTorch logits file: {pytorch_file}")

examples/model-conversion/scripts/utils/common.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+
+import os
+import sys
+
+def get_model_name_from_env_path(env_path_name):
+    model_path = os.getenv(env_path_name)
+    if not model_path:
+        print(f"Error: {env_path_name} environment variable not set")
+        sys.exit(1)
+
+    if not os.path.exists(model_path):
+        print(f"Error: Model file not found: {model_path}")
+        sys.exit(1)
+
+    name = os.path.basename(os.path.normpath(model_path))
+    if name.endswith(".gguf"):
+        name = name[:-5]
+
+    return name

examples/speculative-simple/speculative-simple.cpp

@@ -255,6 +255,8 @@ int main(int argc, char ** argv) {
     LOG_INF("target:\n\n");
     common_perf_print(ctx_tgt, smpl);
 
+    llama_batch_free(batch_tgt);
+
     common_sampler_free(smpl);
     common_speculative_free(spec);
 

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -757,7 +757,8 @@ struct vk_device_struct {
 
     vk_pipeline pipeline_flash_attn_split_k_reduce;
 
-    vk_pipeline pipeline_topk_moe[num_topk_moe_pipelines][TOPK_MOE_COUNT];
+    // [2] is for whether to take n_experts from spec constant (0) or push constant (1)
+    vk_pipeline pipeline_topk_moe[num_topk_moe_pipelines][TOPK_MOE_COUNT][2];
 
     std::vector<vk_pipeline_ref> all_pipelines;
 
@@ -1149,6 +1150,7 @@ static_assert(sizeof(vk_op_multi_add_push_constants) <= 256);
 
 struct vk_op_topk_moe_push_constants {
     uint32_t n_rows;
+    uint32_t n_experts_push;
     uint32_t n_expert_used;
     float clamp_min;
     float clamp_max;
@@ -4204,10 +4206,12 @@ static void ggml_vk_load_shaders(vk_device& device) {
     ggml_vk_create_pipeline(device, device->pipeline_conv2d_dw_whcn_f16_f32, "conv2d_dw_whcn_f16_f32", conv2d_dw_whcn_f16_f32_len, conv2d_dw_whcn_f16_f32_data, "main", 3, sizeof(vk_op_conv2d_dw_push_constants), {512, 1, 1}, {}, 1);
     ggml_vk_create_pipeline(device, device->pipeline_conv2d_dw_cwhn_f16_f32, "conv2d_dw_cwhn_f16_f32", conv2d_dw_cwhn_f16_f32_len, conv2d_dw_cwhn_f16_f32_data, "main", 3, sizeof(vk_op_conv2d_dw_push_constants), {512, 1, 1}, {}, 1);
 
-    for (uint32_t i = 0; i < num_topk_moe_pipelines; ++i) {
-        ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX],      "topk_moe_f32_early_softmax_"+std::to_string(i),       topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 0}, 1, true, true, device->subgroup_size);
-        ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX_NORM], "topk_moe_f32_early_softmax_norm"+std::to_string(i),   topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 1, 0}, 1, true, true, device->subgroup_size);
-        ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_LATE_SOFTMAX],       "topk_moe_f32_late_softmax"+std::to_string(i),         topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 1}, 1, true, true, device->subgroup_size);
+    for (uint32_t use_push = 0; use_push < 2; ++use_push) {
+        for (uint32_t i = 0; i < num_topk_moe_pipelines; ++i) {
+            ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX][use_push],      "topk_moe_f32_early_softmax_"+std::to_string(i),       topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 0, use_push}, 1, true, true, device->subgroup_size);
+            ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_EARLY_SOFTMAX_NORM][use_push], "topk_moe_f32_early_softmax_norm"+std::to_string(i),   topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 1, 0, use_push}, 1, true, true, device->subgroup_size);
+            ggml_vk_create_pipeline2(device, device->pipeline_topk_moe[i][TOPK_MOE_LATE_SOFTMAX][use_push],       "topk_moe_f32_late_softmax"+std::to_string(i),         topk_moe_f32_len, topk_moe_f32_data, "main", 3, sizeof(vk_op_topk_moe_push_constants), {1, 1, 1}, {device->subgroup_size, 1u<<i, 0, 1, use_push}, 1, true, true, device->subgroup_size);
+        }
     }
 
     for (auto &c : compiles) {
@@ -8554,7 +8558,9 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
             uint32_t idx = (uint32_t)ceilf(log2f(float(dst->ne[0])));
             GGML_ASSERT(idx < num_topk_moe_pipelines);
             topk_moe_mode mode = ggml_vk_num_additional_ops_to_topk_moe_mode(ctx->num_additional_fused_ops);
-            return ctx->device->pipeline_topk_moe[idx][mode];
+            // use n_experts from push constant if it's not equal to the power of two spec constant
+            bool use_push = dst->ne[0] != (1u << idx);
+            return ctx->device->pipeline_topk_moe[idx][mode][use_push];
         }
 
         if (src0->type == GGML_TYPE_F32 && (src1 == nullptr || src1->type == GGML_TYPE_F32) && dst->type == GGML_TYPE_F32) {
@@ -10158,6 +10164,7 @@ static void ggml_vk_topk_moe(ggml_backend_vk_context * ctx, vk_context& subctx,
 
     vk_op_topk_moe_push_constants pc {};
     pc.n_rows = n_rows;
+    pc.n_experts_push = n_experts;
     pc.n_expert_used = n_expert_used;
     if (mode == TOPK_MOE_EARLY_SOFTMAX_NORM) {
         ggml_tensor * clamp = cgraph->nodes[node_idx + 7];
@@ -12832,8 +12839,7 @@ static bool ggml_vk_can_fuse_topk_moe(ggml_backend_vk_context * ctx, const struc
     }
 
     const int n_expert = softmax->ne[0];
-    // n_expert must be a power of 2
-    if (!is_pow2(n_expert) || n_expert > (1 << (num_topk_moe_pipelines-1))) {
+    if (n_expert > (1 << (num_topk_moe_pipelines-1))) {
         return false;
     }
 

ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp

@@ -10,6 +10,7 @@
 layout (push_constant) uniform parameter
 {
     uint n_rows;
+    uint n_experts_push;
     uint n_expert_used;
     float clamp_min;
     float clamp_max;
@@ -18,11 +19,16 @@ layout (push_constant) uniform parameter
 layout(local_size_x_id = 0, local_size_y = 4, local_size_z = 1) in;
 
 layout(constant_id = 0) const uint WARP_SIZE = 32;
-layout(constant_id = 1) const uint n_experts = 512;
+layout(constant_id = 1) const uint n_experts_spec = 512;
 layout(constant_id = 2) const bool with_norm = true;
 layout(constant_id = 3) const bool late_softmax = false;
+layout(constant_id = 4) const bool nexperts_use_push = false;
 
-const uint experts_per_thread = (n_experts > WARP_SIZE) ? n_experts / WARP_SIZE : 1;
+uint n_experts = nexperts_use_push ? n_experts_push : n_experts_spec;
+
+#define CEIL_DIV(a, b) (((a) + (b) - 1) / (b))
+
+const uint experts_per_thread = CEIL_DIV(n_experts_spec, WARP_SIZE);
 
 layout (binding = 0, std430) readonly buffer Logits {float logits[];};
 layout (binding = 1, std430) writeonly buffer Weights {float weights[];};
@@ -94,7 +100,7 @@ void main() {
     }
 
     if (!late_softmax) {
-        softmax_warp_inplace(wt, n_experts, lane, false);
+        softmax_warp_inplace(wt, n_experts, lane, nexperts_use_push);
     }
 
     // at this point, each thread holds a portion of softmax,

pyrightconfig.json

@@ -1,5 +1,5 @@
 {
-  "extraPaths": ["gguf-py"],
+  "extraPaths": ["gguf-py", "examples/model-conversion/scripts"],
   "pythonVersion": "3.9",
   "pythonPlatform": "All",
   "reportUnusedImport": "warning",

tests/test-backend-ops.cpp

@@ -7971,8 +7971,12 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
 
     for (bool with_norm : {false, true}) {
         test_cases.emplace_back(new test_topk_moe({8, 22, 1, 1}, 4, with_norm));
+        test_cases.emplace_back(new test_topk_moe({31, 22, 1, 1}, 8, with_norm));
         test_cases.emplace_back(new test_topk_moe({32, 22, 1, 1}, 8, with_norm));
+        test_cases.emplace_back(new test_topk_moe({40, 22, 1, 1}, 8, with_norm));
+        test_cases.emplace_back(new test_topk_moe({71, 22, 1, 1}, 8, with_norm));
         test_cases.emplace_back(new test_topk_moe({128, 1, 1, 1}, 128, with_norm));
+        test_cases.emplace_back(new test_topk_moe({129, 1, 1, 1}, 128, with_norm));
     }
 
     test_cases.emplace_back(new test_topk_moe({ 8, 22, 1, 1 }, 4, /*with_norm*/ false, /*delayed_softmax*/ true));