From 9b4ff1ba01712741d9309161ba31039a902b764d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jie=20Fu=20=28=E5=82=85=E6=9D=B0=29?= Date: Thu, 11 Jul 2024 12:15:29 +0800 Subject: [PATCH] [Doc] Update description of vLLM support for CPUs (#6003) --- README.md | 2 +- docs/source/getting_started/cpu-installation.rst | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 3e0da945d9be8..cced85f17e257 100644 --- a/README.md +++ b/README.md @@ -59,7 +59,7 @@ vLLM is flexible and easy to use with: - Tensor parallelism support for distributed inference - Streaming outputs - OpenAI-compatible API server -- Support NVIDIA GPUs, AMD GPUs, Intel CPUs and GPUs +- Support NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs and GPUs, PowerPC CPUs - (Experimental) Prefix caching support - (Experimental) Multi-lora support diff --git a/docs/source/getting_started/cpu-installation.rst b/docs/source/getting_started/cpu-installation.rst index a9544e8a59a3d..1c97515dbecd9 100644 --- a/docs/source/getting_started/cpu-installation.rst +++ b/docs/source/getting_started/cpu-installation.rst @@ -20,7 +20,7 @@ Requirements * OS: Linux * Compiler: gcc/g++>=12.3.0 (optional, recommended) -* Instruction set architecture (ISA) requirement: AVX512 is required. +* Instruction set architecture (ISA) requirement: AVX512 (optional, recommended) .. _cpu_backend_quick_start_dockerfile: