xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-02 04:34:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Remove block size constraint (#11723)

Browse Source
This commit is contained in:
Cody Yu 2025-01-05 20:49:55 -08:00 committed by GitHub
parent 402d378360
commit 408e560015
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/config.py
View File

@ -1015,11 +1015,6 @@ class CacheConfig:
raise ValueError(
"GPU memory utilization must be less than 1.0. Got "
f"{self.gpu_memory_utilization}.")
from vllm.platforms import current_platform
if (current_platform.is_cuda() and self.block_size is not None
and self.block_size > 32):
raise ValueError("CUDA Paged Attention kernel only supports "
f"block sizes up to 32. Got {self.block_size}.")
def _verify_cache_dtype(self) -> None:
if self.cache_dtype == "auto":