llama.cpp/ggml/src at b10813 - llama.cpp - Gitea: Git with a cup of tea

wylab/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-15 18:13:29 +02:00

Files

T

History

4acf4a4cb8 opencl: add Adreno xmem SDPA path (#26331 )

* opencl: add Adreno xmem SDPA path

Assisted-by: Codex

* Removed the Adreno-specific queue profiling override

* Clean up formatting

* 修复数值误差优化gqa/mask attn

Assisted-by: Codex

* add env GGML_OPENCL_XMEM_SDPA

Assisted-by: OpenAI Codex

---------

Co-authored-by: happyyzy <happyyzy@users.noreply.github.com>

2026-09-04 10:12:05 -07:00

..

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081 )

2026-08-11 09:20:46 +03:00

ggml: add SWIGLU_CLAMP (#27930 )

2026-08-30 23:00:02 +08:00

ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332 )

2026-09-04 08:55:50 +03:00

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177 )

2026-09-04 10:22:01 +03:00

ggml: add SWIGLU_CLAMP (#27930 )

2026-08-30 23:00:02 +08:00

ggml-hexagon: add F16 support for unary ops (#28228 )

2026-09-02 12:59:36 -07:00

ggml-hip : remove -funsafe-math-optimizations (#26696 )

2026-08-13 08:38:02 +02:00

metal : add remaining fa-vec tunings for M3 Max (#28373 )

2026-09-04 11:46:31 +02:00

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177 )

2026-09-04 10:22:01 +03:00

opencl: add Adreno xmem SDPA path (#26331 )

2026-09-04 10:12:05 -07:00

ggml: add SWIGLU_CLAMP (#27930 )

2026-08-30 23:00:02 +08:00

sync : ggml (#28379 )

2026-09-04 14:39:19 +03:00

sycl: fuse rms_norm+mul+add and add+add residual chains (#27610 )

2026-09-04 00:05:40 -04:00

ggml: allow passing alloc dependencies in graph_optimize (#27301 )

2026-08-30 11:34:20 +08:00

vulkan: fix FA dequant path engagement (#28190 )

2026-09-03 10:40:34 +02:00

webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_backend_tensor_get() implementation (#28045 )

2026-08-31 16:04:38 +02:00

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081 )

2026-08-11 09:20:46 +03:00

CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (#26678 )

2026-08-20 15:42:26 +02:00

CMakeLists.txt

ggml : replace compile definitions with version.h.in (#28364 )

2026-09-04 10:28:23 +02:00

ggml-alloc.c

ggml : fix ggml_clamp (#27644 )

2026-08-24 10:43:04 +03:00

ggml-backend-dl.cpp

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

2026-01-29 12:33:21 -08:00

ggml-backend-dl.h

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

2026-01-29 12:33:21 -08:00

ggml-backend-impl.h

sync : ggml (#28379 )

2026-09-04 14:39:19 +03:00

ggml-backend-meta.cpp

ggml-meta: propagate buffer usage and call init on the new tensors (#27586 )

2026-08-26 08:27:51 +03:00

ggml-backend-reg.cpp

ggml : don't crash when backend search path can't be read (#28271 )

2026-09-04 10:24:06 +03:00

ggml-backend.cpp

sync : ggml (#28379 )

2026-09-04 14:39:19 +03:00

ggml-common.h

AVX2: Speed up large batch size prompt processing of IQ models (#27402 )

2026-08-31 14:33:50 -04:00

ggml-feats.h

ggml : fix arm builds, unused var (#26991 )

2026-08-13 07:57:24 +03:00

ggml-impl.h

ggml: add graph_reused (#21764 )

2026-04-16 17:21:28 +08:00

ggml-opt.cpp

fix: free ctx_copy in ggml_opt_free to plug per-training-session leak (#21592 )

2026-04-08 17:40:15 +02:00

ggml-quants.c

Add Q2_0 quantization: type definition and CPU backend (#24448 )

2026-07-07 12:05:47 -07:00

ggml-quants.h

Add Q2_0 quantization: type definition and CPU backend (#24448 )

2026-07-07 12:05:47 -07:00

ggml-threading.cpp

…

ggml-threading.h

…

ggml-version.h.in

ggml : replace compile definitions with version.h.in (#28364 )

2026-09-04 10:28:23 +02:00

ggml.c

ggml : replace compile definitions with version.h.in (#28364 )

2026-09-04 10:28:23 +02:00

ggml.cpp

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

2025-06-01 13:43:57 +03:00

gguf.cpp

gguf : harden loader against malformed tensor dims and metadata types (#25596 )

2026-08-12 15:07:48 +03:00