]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)
authorRémy O <redacted>
Thu, 6 Mar 2025 01:26:10 +0000 (02:26 +0100)
committerGeorgi Gerganov <redacted>
Sat, 8 Mar 2025 13:13:01 +0000 (15:13 +0200)
commit8dcadf736b2fdfff122631cfebec3c9006272593
tree0f917bc5a1dabbb2d2f14e1efe40e27d64c00761
parent93986b61e0f38d0362b5466528adbdd3a01a394f
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)

* ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions

* cmake: Add GGML_BMI2 build option

* ggml: enable BMI2 on relevant CPU variants

* ggml-cpu: include BMI2 in backend score

* ggml-cpu: register BMI2 in ggml_backend_cpu_get_features

* ggml-cpu: add __BMI2__ define when using MSVC
ggml/CMakeLists.txt
ggml/include/ggml-cpu.h
ggml/src/CMakeLists.txt
ggml/src/ggml-cpu/CMakeLists.txt
ggml/src/ggml-cpu/cpu-feats-x86.cpp
ggml/src/ggml-cpu/ggml-cpu-quants.c
ggml/src/ggml-cpu/ggml-cpu.c
ggml/src/ggml-cpu/ggml-cpu.cpp