xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 07:07:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CPU] Change default block_size for CPU backend (#16002)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang 2025-04-05 00:39:05 +08:00 committed by GitHub
parent 95862f7b4d
commit 2386803f2a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/platforms/cpu.py
View File

@ -2,6 +2,7 @@
import os import os
import sys import sys
from importlib.util import find_spec
from typing import TYPE_CHECKING, Optional from typing import TYPE_CHECKING, Optional
import psutil import psutil
@ -68,8 +69,15 @@ class CpuPlatform(Platform):
cache_config = vllm_config.cache_config cache_config = vllm_config.cache_config
ipex_avaliable = find_spec("intel_extension_for_pytorch") is not None
if cache_config and cache_config.block_size is None: if cache_config and cache_config.block_size is None:
cache_config.block_size = 16 cache_config.block_size = 128 if ipex_avaliable else 16
if not ipex_avaliable and cache_config.block_size != 16:
raise RuntimeError(
f"--block-size={cache_config.block_size} requires"
" intel_extension_for_pytorch")
scheduler_config = vllm_config.scheduler_config scheduler_config = vllm_config.scheduler_config
if ((scheduler_config.chunked_prefill_enabled if ((scheduler_config.chunked_prefill_enabled