]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 4162522)
[SYCL] Support Q4_1, Q5_0, Q5_1 in Flash-attention (#23812)
authorNeo Zhang <redacted>
Mon, 1 Jun 2026 06:53:53 +0000 (14:53 +0800)
committerGitHub <redacted>
Mon, 1 Jun 2026 06:53:53 +0000 (09:53 +0300)
commita51142497a12e0c3d86c6b310bf4b65139adf02e
tree337e5155dcd597ab88e80a8c2c8cb396b852391dtree
parent416252268825d5f0b24568d2c7f99481d7c6d077commit | diff
[SYCL] Support Q4_1, Q5_0, Q5_1 in Flash-attention (#23812)

* support Q4_1, Q5_0, Q5_1

* update ut case
docs/ops/SYCL.csv diff | blob | history
ggml/src/ggml-sycl/common.hpp diff | blob | history
ggml/src/ggml-sycl/fattn-common.hpp diff | blob | history
Packaging of ggml-org/llama.cpp