Skip to content

Enable prefix caching with full cuda graphs #19617

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 4 commits into from
Jun 15, 2025
+0 −1
Merged

Enable prefix caching with full cuda graphs #19617

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e8f07e5
[Bugfix] Enable prefix caching with full cuda graphs
WoosukKwon Jun 13, 2025
b10f335
minor
WoosukKwon Jun 13, 2025
23b2d38
merge
WoosukKwon Jun 15, 2025
e56aad4
Merge branch 'main' into full-cuda-graph-prefix-caching
WoosukKwon Jun 15, 2025
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
1 change: 0 additions & 1 deletion vllm/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4495,7 +4495,6 @@ def __post_init__(self):
"full_cuda_graph is not supported with "
"cascade attention. Disabling cascade attention.")
self.model_config.disable_cascade_attn = True
self.cache_config.enable_prefix_caching = False

if (self.kv_events_config is not None
and self.kv_events_config.enable_kv_cache_events
Expand Down