mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 19:34:35 +00:00
3407364776
* 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 |
||
|---|---|---|
| .. | ||
| bench.yml.disabled | ||
| build.yml | ||
| close-issue.yml | ||
| docker.yml | ||
| editorconfig.yml | ||
| gguf-publish.yml | ||
| labeler.yml | ||
| nix-ci-aarch64.yml | ||
| nix-ci.yml | ||
| nix-flake-update.yml | ||
| nix-publish-flake.yml | ||
| python-check-requirements.yml | ||
| python-lint.yml | ||
| python-type-check.yml | ||
| server.yml | ||