Isaac ad218df420 metal : add remaining fa-vec tunings for M3 (llama/28396) ...

* addition of m3 in fa_vec_tuned_table

* adding q4_0,q4_1,q5_0,q5_1 in ggml-metal-tuning

* Fix formatting in ggml-metal-tuning.cpp

2026-09-14 20:45:06 +03:00

..

ggml-blas

…

ggml-cann

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml-cpu

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

2026-09-04 13:39:42 +03:00

ggml-cuda

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (llama/28177)

2026-09-04 13:39:43 +03:00

ggml-et

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml-hexagon

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

2026-09-04 13:39:41 +03:00

ggml-hip

…

ggml-metal

metal : add remaining fa-vec tunings for M3 (llama/28396)

2026-09-14 20:45:06 +03:00

ggml-musa

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (llama/28177)

2026-09-04 13:39:43 +03:00

ggml-opencl

opencl: extend the elementwise and data‐movement op coverage (#27633)

2026-09-14 20:45:06 +03:00

ggml-openvino

ggml: add SWIGLU_CLAMP (llama/27930)

2026-09-04 13:39:35 +03:00

ggml-rpc

ggml : rename and make private ggml_op_alloc_size_may_expand() (ggml/0)

2026-09-04 13:39:43 +03:00

ggml-sycl

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

2026-09-04 13:39:42 +03:00

ggml-virtgpu

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

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

ggml-vulkan

vulkan: fix FA dequant path engagement (llama/28190)

2026-09-04 13:39:41 +03:00

ggml-webgpu

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

2026-09-04 13:39:37 +03:00

ggml-zdnn

…

ggml-zendnn

…

CMakeLists.txt

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

2026-09-04 13:39:43 +03:00

ggml-alloc.c

…

ggml-backend-dl.cpp

…

ggml-backend-dl.h

…

ggml-backend-impl.h

ggml : rename and make private ggml_op_alloc_size_may_expand() (ggml/0)

2026-09-04 13:39:43 +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

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

2026-09-04 13:39:43 +03:00

ggml-backend.cpp

ggml : rename and make private ggml_op_alloc_size_may_expand() (ggml/0)

2026-09-04 13:39:43 +03:00

ggml-common.h

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

2026-09-04 13:39:37 +03:00

ggml-feats.h

…

ggml-impl.h

…

ggml-opt.cpp

…

ggml-quants.c

…

ggml-quants.h

…

ggml-threading.cpp

…

ggml-threading.h

…

ggml-version.h.in

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

2026-09-04 13:39:43 +03:00

ggml.c

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

2026-09-04 13:39:43 +03:00

ggml.cpp

…

gguf.cpp

…