[Doc] Update description of vLLM support for CPUs (#6003)

439c8458 · Jie Fu (傅杰) · GitHub · 99ded1e1 · 439c8458 · 439c8458
Unverified Commit 439c8458 authored Jul 11, 2024 by Jie Fu (傅杰) Committed by GitHub Jul 10, 2024
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 2 deletions

README.md README.md +1 -1

docs/source/getting_started/cpu-installation.rst docs/source/getting_started/cpu-installation.rst +1 -1

No files found.
--- 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


--- 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: