]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: e235b26)
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)
authorluoyu-intel <redacted>
Fri, 5 Jul 2024 05:06:13 +0000 (05:06 +0000)
committerGitHub <redacted>
Fri, 5 Jul 2024 05:06:13 +0000 (13:06 +0800)
commita9554e20b66546b0549aebe2e1034bc8afe9d809
tree93b5356b2f138283994be0bb5d7dd08476aa0683tree
parente235b267a2539d043734ff340eff74107722eb57commit | diff
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)

* fix group_norm ut

* split softmax

* fix softmax

* add concat support condition

* revert debug code

* move QK_WARP_SIZE to presets.hpp
ggml/src/CMakeLists.txt diff | blob | history
ggml/src/ggml-sycl.cpp diff | blob | history
ggml/src/ggml-sycl/backend.hpp diff | blob | history
ggml/src/ggml-sycl/dmmv.cpp diff | blob | history
ggml/src/ggml-sycl/norm.cpp diff | blob | history
ggml/src/ggml-sycl/presets.hpp diff | blob | history
ggml/src/ggml-sycl/softmax.cpp [new file with mode: 0644] blob
ggml/src/ggml-sycl/softmax.hpp [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp