]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
sycl: refactor quantization to q8_1 (llama/14815)
authorAlberto Cabrera Pérez <redacted>
Mon, 28 Jul 2025 10:05:53 +0000 (11:05 +0100)
committerGeorgi Gerganov <redacted>
Sat, 2 Aug 2025 14:51:21 +0000 (17:51 +0300)
commit1f45741755b58ad2e7281250e5da4c69c9abe710
treedf96bb211e427a9f0b07e30c53655ad27c6768e6
parent4af7c56643fc5b4dda156cfaf6b05f7ea7ec0680
sycl: refactor quantization to q8_1 (llama/14815)

* sycl: quantization to q8_1 refactor

* Refactored src1 copy logic in op_mul_mat
src/ggml-sycl/backend.hpp
src/ggml-sycl/ggml-sycl.cpp
src/ggml-sycl/quantize.hpp [new file with mode: 0644]