Eve 3407364776 Q6_K AVX improvements (#10118) ... * q6_k instruction reordering attempt * better subtract method * should be theoretically faster small improvement with shuffle lut, likely because all loads are already done at that stage * optimize bit fiddling * handle -32 offset separately. bsums exists for a reason! * use shift * Update ggml-quants.c * have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86		2024-11-04 23:06:31 +01:00
..
bench.yml.disabled	ggml-backend : add device and backend reg interfaces (#9707)	2024-10-03 01:49:47 +02:00
build.yml	Q6_K AVX improvements (#10118)	2024-11-04 23:06:31 +01:00
close-issue.yml	ci : fine-grant permission (#9710)	2024-10-04 11:47:19 +02:00
docker.yml	musa: add docker image support (#9685)	2024-10-10 20:10:37 +02:00
editorconfig.yml
gguf-publish.yml
labeler.yml
nix-ci-aarch64.yml	ci : fine-grant permission (#9710)	2024-10-04 11:47:19 +02:00
nix-ci.yml	ci : fine-grant permission (#9710)	2024-10-04 11:47:19 +02:00
nix-flake-update.yml
nix-publish-flake.yml
python-check-requirements.yml
python-lint.yml
python-type-check.yml
server.yml