]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: be3bbd6)
ggml-cpu : add chunking support to mul_mat_id (#11666)
authorDiego Devesa <redacted>
Thu, 13 Feb 2025 00:02:38 +0000 (01:02 +0100)
committerGitHub <redacted>
Thu, 13 Feb 2025 00:02:38 +0000 (01:02 +0100)
commita394039db004c6ee00098250d160b5aa018c2314
tree37652b350164d3ed90e0fbbdececc99631d6eed1tree
parentbe3bbd62153820ff6d358c817360927f429105c4commit | diff
ggml-cpu : add chunking support to mul_mat_id (#11666)

* ggml-cpu : add chunking support to mul_mat_id

* allocate chunk counter in wdata
parallelize src1 quantization by column to allows parallelization even when there is only one row

* disable for arm

* cleanup

* better way to disable for arm

* fix uninitialized counter when using 1 thread only

* revert test-backend-ops changes
ggml/src/ggml-cpu/ggml-cpu.c diff | blob | history
Packaging of ggml-org/llama.cpp