biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Disable cascade attention by default (#36318)

Browse Source
This commit is contained in:
Michael Goin
2026-03-11 11:12:23 +01:00
committed by GitHub
parent 09b6f99852
commit 9c34e9d24f
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
vllm/config/model.py
View File

@@ -217,12 +217,13 @@ class ModelConfig:
"""Whether to disable sliding window. If True, we will disable the sliding
window functionality of the model, capping to sliding window size. If the
model does not support sliding window, this argument is ignored."""
disable_cascade_attn: bool = False
disable_cascade_attn: bool = True
"""Disable cascade attention for V1. While cascade attention does not
change the mathematical correctness, disabling it could be useful for
preventing potential numerical issues. Note that even if this is set to
False, cascade attention will be only used when the heuristic tells that
it's beneficial."""
preventing potential numerical issues. This defaults to True, so users
must opt in to cascade attention by setting this to False. Even when this
is set to False, cascade attention will only be used when the heuristic
tells that it's beneficial."""
skip_tokenizer_init: bool = False
"""Skip initialization of tokenizer and detokenizer. Expects valid
`prompt_token_ids` and `None` for prompt from the input. The generated