@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 925d2f1908
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 00:45 UTC

[Doc] Fix typo for x86 CPU installation (#12514)

Signed-off-by: Jun Duan <jun.duan.phd@outlook.com>

Jun Duan committed Jan 28, 2025 at 11:37 UTC 925d2f19089b50736ce5e0f2ba0c9b7f3da6fb15
1 file changed +1 -1
docs/source/getting_started/installation/cpu/x86.inc.md
+1 -1
@@ -18,7 +18,7 @@ vLLM initially supports basic model inferencing and serving on x86 CPU platform,
18 :::
19
20 ```{note}
21 -- AVX512_BF16 is an extension ISA provides native BF16 data type conversion and vector product instructions, will brings some performance improvement compared with pure AVX512. The CPU backend build script will check the host CPU flags to determine whether to enable AVX512_BF16.
21 +- AVX512_BF16 is an extension ISA provides native BF16 data type conversion and vector product instructions, which brings some performance improvement compared with pure AVX512. The CPU backend build script will check the host CPU flags to determine whether to enable AVX512_BF16.
22 - If you want to force enable AVX512_BF16 for the cross-compilation, please set environment variable `VLLM_CPU_AVX512BF16=1` before the building.
23 ```
24