LunalFresh e5c9e3e3e9 hip : optimize Q2_0 dot-product path for gfx1201 (llama/26753) ...

* hip/gfx1201: optimize q2_0 vec_dot_q2_0_q8_1 with native amdgcn perm

* Broadened HIP's Q2_0 perm optimization

* Remove redundant HIP perm availability guard

* Optimize HIP Q2_0 MMQ unpack with native perm

* cuda: label HIP preprocessor guard

* cuda: label HIP preprocessor guard

* Restore MMQ tile index handling

2026-09-04 13:39:34 +03:00

..

ggml-blas

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

2026-08-14 22:16:06 +03:00

ggml-cann

ggml: add ggml_rope_set_offset (+ metal support) (llama/27120)

2026-08-21 19:23:26 +03:00

ggml-cpu

ggml : fix conv_transpose_2d for multiple batches (llama/26132)

2026-09-04 13:39:32 +03:00

ggml-cuda

hip : optimize Q2_0 dot-product path for gfx1201 (llama/26753)

2026-09-04 13:39:34 +03:00

ggml-et

ggml: add ggml_rope_set_offset (+ metal support) (llama/27120)

2026-08-21 19:23:26 +03:00

ggml-hexagon

hexagon: support for device discovery and create sessions on demand (llama/27785)

2026-09-04 13:39:33 +03:00

ggml-hip

ggml-hip : remove -funsafe-math-optimizations (llama/26696)

2026-08-14 22:16:06 +03:00

ggml-metal

metal: add fa-vec tunings for M3 Ultra (llama/27999)

2026-09-04 13:39:34 +03:00

ggml-musa

ggml-cuda: native bf16 flash attention for vec kernel (llama/20525)

2026-03-29 15:04:36 +03:00

ggml-opencl

opencl: use a better matmul path on two Adreno GPU generations (llama/27640)

2026-09-04 13:39:33 +03:00

ggml-openvino

OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU, and new ops (llama/27843)

2026-09-04 13:39:31 +03:00

ggml-rpc

ggml : add ggml_backend_op_alloc_size_may_expand, use it in RPC (llama/27960)

2026-09-04 13:39:34 +03:00

ggml-sycl

sycl: split long rows in TOP_K instead of one work-group per row (llama/27847)

2026-09-04 13:39:33 +03:00

ggml-virtgpu

ggml: allow passing alloc dependencies in graph_optimize (llama/27301)

2026-09-04 13:39:33 +03:00

ggml-vulkan

ggml: allow passing alloc dependencies in graph_optimize (llama/27301)

2026-09-04 13:39:33 +03:00

ggml-webgpu

webgpu : fix handling of infinity values during ARGSORT and TOP_K (llama/27538)

2026-08-25 15:28:56 +03:00

ggml-zdnn

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

2026-08-14 22:16:06 +03:00

ggml-zendnn

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

2026-08-21 19:23:26 +03:00

CMakeLists.txt

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

2026-08-21 19:23:26 +03:00

ggml-alloc.c

ggml : fix ggml_clamp (llama/27644)

2026-08-25 15:28:56 +03:00

ggml-backend-dl.cpp

…

ggml-backend-dl.h

…

ggml-backend-impl.h

ggml: allow passing alloc dependencies in graph_optimize (llama/27301)

2026-09-04 13:39:33 +03:00

ggml-backend-meta.cpp

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

2026-09-04 13:39:29 +03:00

ggml-backend-reg.cpp

sync : ggml (#3962)

2026-07-31 09:11:28 +02:00

ggml-backend.cpp

ggml : add ggml_backend_op_alloc_size_may_expand, use it in RPC (llama/27960)

2026-09-04 13:39:34 +03:00

ggml-common.h

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

2026-07-10 13:06:42 +03:00

ggml-feats.h

ggml : fix arm builds, unused var (llama/26991)

2026-08-14 22:16:06 +03:00

ggml-impl.h

ggml: add graph_reused (llama/21764)

2026-04-30 11:29:11 +03:00

ggml-opt.cpp

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

2026-04-30 11:29:03 +03:00

ggml-quants.c

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

2026-07-10 13:06:42 +03:00

ggml-quants.h

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

2026-07-10 13:06:42 +03:00

ggml-threading.cpp

…

ggml-threading.h

…

ggml.c

ggml : fix ggml_clamp (llama/27644)

2026-08-25 15:28:56 +03:00

ggml.cpp

…

gguf.cpp

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

2026-08-14 22:16:06 +03:00