youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Remove V0 attention backends (#25351)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-09-21 16:03:28 -07:00
committed by GitHub
parent af7dfb0d1a
commit bc6e542d9f
28 changed files with 143 additions and 7376 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/offline_inference/qwen_1m.py
View File

@ -5,7 +5,6 @@ from urllib.request import urlopen
from vllm import LLM, SamplingParams
os.environ["VLLM_ATTENTION_BACKEND"] = "DUAL_CHUNK_FLASH_ATTN"
os.environ["VLLM_ALLOW_LONG_MAX_MODEL_LEN"] = "1"