Skip to content

Commit f3eeb5d

Browse files
authored
Fix description on AVX512 builds
1 parent fa4be76 commit f3eeb5d

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,6 @@ Server images are tagged in the format of `server-<ssl>-<avx>`.
2424
- `noavx`: All AVX-related optimizations are disabled. Do not use this build unless you are working around some known bug, or running LLMs on a 10-year-old potato.
2525
- `avx`: (Only) AVX instruction set is enabled. Might be useful if you are using some old CPUs that don't support AVX2.
2626
- `avx2`: AVX2 instruction set is enabled. This build should support most modern/recent CPUs with reasonable performance.
27-
- `avx512`: AVX512 and AVX512-VNNI instruction sets are enabled. Currently only some high-end or server-grade CPUs support these instruction sets, so check your hardware specs before using this build.
27+
- `avx512`: AVX512 base instruction set is enabled. Currently only some high-end or server-grade CPUs support this instruction set, so check your hardware specs before using this build.
2828
- `oneapi`: Experimental build with the Intel oneAPI compiler, inspired by ggerganov/llama.cpp#5067. Offers a ~30% speed increase (~20tok/s vs ~15tok/s) in prompt processing on my machine compared to `avx2` builds. Not updated daily.
2929

0 commit comments

Comments
 (0)