Eurekatic 4aa6ffba25 sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062) ... * sycl: Q4_K Weight unpack optimization and reuse between destination Columns * sycl: Q4_K small N (N=2..4) + two output rows by subgroup reuse of activation between two rows. * sycl: gate Q4_K two-row reuse for small N=2 * sycl: Fix on magic number now uses Q4_K_MMVQ_ROW_PAIR_MIN_NROWS=6272 for it, added tests for coverage around Q4_K_MMVQ_ROW_PAIR_MIN_NROWS with perf support to test Q4_K MUL_MAT, applied the same reuse pattern to the activation as the weights. Assisted-by: GPT-5.6 Sol --------- Co-authored-by: RaulAbejonDelgado <raul.abejon.delgado@gmail.com>		2026-09-03 14:59:06 +08:00
..
cmake	kleidiai: Rework KleidiAI Build System/Integration (#26077)	2026-08-25 14:07:29 -07:00
include	CUDA + ggml: add sparse-fa for DSV4/GLM (#27970)	2026-09-02 17:27:37 +03:00
src	sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062)	2026-09-03 14:59:06 +08:00
.gitignore
CMakeLists.txt	metal : add metallib build support for xcframework (#28163)	2026-09-02 07:45:56 +08:00