From 0eed516951e0c5b834d0e59b86fd6b555fa90f65 Mon Sep 17 00:00:00 2001 From: Kay Yan Date: Tue, 24 Jun 2025 12:04:11 +0800 Subject: [PATCH] [doc] Fix broken link in the installation for CPU (#19980) Signed-off-by: Kay Yan --- docs/getting_started/installation/cpu/arm.inc.md | 2 +- docs/getting_started/installation/cpu/x86.inc.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/getting_started/installation/cpu/arm.inc.md b/docs/getting_started/installation/cpu/arm.inc.md index 59b71dcaf911a..6c05900cf45c1 100644 --- a/docs/getting_started/installation/cpu/arm.inc.md +++ b/docs/getting_started/installation/cpu/arm.inc.md @@ -23,7 +23,7 @@ ARM CPU backend currently supports Float32, FP16 and BFloat16 datatypes. # --8<-- [end:pre-built-wheels] # --8<-- [start:build-wheel-from-source] ---8<-- "docs/getting_started/installation/cpu/cpu/build.inc.md" +--8<-- "docs/getting_started/installation/cpu/build.inc.md" Testing has been conducted on AWS Graviton3 instances for compatibility. diff --git a/docs/getting_started/installation/cpu/x86.inc.md b/docs/getting_started/installation/cpu/x86.inc.md index 9434eeea8b4a1..0412d4ccef00b 100644 --- a/docs/getting_started/installation/cpu/x86.inc.md +++ b/docs/getting_started/installation/cpu/x86.inc.md @@ -24,7 +24,7 @@ vLLM initially supports basic model inferencing and serving on x86 CPU platform, # --8<-- [end:pre-built-wheels] # --8<-- [start:build-wheel-from-source] ---8<-- "docs/getting_started/installation/cpu/cpu/build.inc.md" +--8<-- "docs/getting_started/installation/cpu/build.inc.md" !!! note - 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.