Skip to content

[None][fix] Add synchronize for kvcache cleanup #7537

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

Closed
pengbowang-nv wants to merge 1 commit into from
Closed

[None][fix] Add synchronize for kvcache cleanup #7537

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 1 addition & 0 deletions tensorrt_llm/_torch/pyexecutor/model_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -657,6 +657,7 @@ def clean_up_kv_cache():
# Zero the KV cache; NaNs may be introduced during warmup
for layer_idx in kv_cache_manager.layer_offsets.keys():
kv_cache_manager.get_buffers(layer_idx).zero_()
torch.cuda.synchronize()

stack.callback(clean_up_kv_cache)

Expand Down