]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 44008ce)
ggml-cpu: use LUT for converting e8->f32 scales on x86 (#19288)
authorAman Gupta <redacted>
Wed, 4 Feb 2026 01:43:29 +0000 (09:43 +0800)
committerGitHub <redacted>
Wed, 4 Feb 2026 01:43:29 +0000 (09:43 +0800)
commit2ceda3f6622661af839c19767705f33fb9f6cdd2
tree6626ced4fe010241bedbae4754229757de0a2fc8tree
parent44008ce8f93a5dc025a40ba3150ab9d119af22f0commit | diff
ggml-cpu: use LUT for converting e8->f32 scales on x86 (#19288)

* ggml-cpu: use LUT for converting e8->f32 scales on x86

* add dispatch based on macro
ggml/src/ggml-cpu/arch/x86/quants.c diff | blob | history
ggml/src/ggml-cpu/ggml-cpu.c diff | blob | history
ggml/src/ggml-cpu/simd-mappings.h diff | blob | history
Packaging of ggml-org/llama.cpp