Skip to content

[CPU] Change default block_size for CPU backend #16002

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 4, 2025
Merged

[CPU] Change default block_size for CPU backend #16002

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion vllm/platforms/cpu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

import os
import sys
from importlib.util import find_spec
from typing import TYPE_CHECKING, Optional

import psutil
Expand Down Expand Up @@ -68,8 +69,15 @@ def check_and_update_config(cls, vllm_config: VllmConfig) -> None:

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:
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
if ((scheduler_config.chunked_prefill_enabled
Expand Down