]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a5771c9)
sycl: refactor quantization to q8_1 (#14815)
authorAlberto Cabrera Pérez <redacted>
Mon, 28 Jul 2025 10:05:53 +0000 (11:05 +0100)
committerGitHub <redacted>
Mon, 28 Jul 2025 10:05:53 +0000 (11:05 +0100)
commitafc0e8969896ada62238da07b98731e5a4b12ba4
treece618e66604ec9ce6c96795ee064d467fd00d182tree
parenta5771c9eea801f573dc7375416e4c3306543563dcommit | diff
sycl: refactor quantization to q8_1  (#14815)

* sycl: quantization to q8_1 refactor

* Refactored src1 copy logic in op_mul_mat
ggml/src/ggml-sycl/backend.hpp diff | blob | history
ggml/src/ggml-sycl/ggml-sycl.cpp diff | blob | history
ggml/src/ggml-sycl/quantize.hpp [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp