xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-30 15:31:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1][Minor] Remove outdated comment (#12968)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-02-08 12:48:30 -08:00 committed by GitHub
parent 86222a3dab
commit 870c37481e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/core/kv_cache_manager.py
View File

@ -205,8 +205,6 @@ class KVCacheManager:
# Should not exceed the maximum number of blocks per request.
# This is especially because the block table has the shape
# [..., max_num_blocks_per_req].
# TODO(woosuk): Check and reject requests if
# num_prompt_tokens + max_tokens > max_model_len.
self.max_num_blocks_per_req - len(req_blocks),
)
assert num_new_blocks > 0