Skip to content

Clear the Mamba cache table if the running queue is empty #2046

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 1 commit into from
Oct 20, 2025
Merged

Clear the Mamba cache table if the running queue is empty #2046

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
5 changes: 5 additions & 0 deletions vllm/worker/hpu_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -249,6 +249,11 @@ def execute_model(
'VLLM_HPU_LOG_STEP_CPU_FALLBACKS_ALL', '0') != '0'
log_cpu_fallbacks = os.environ.get('VLLM_HPU_LOG_STEP_CPU_FALLBACKS',
'0') != '0' or log_cpu_fallbacks_all

# Empty the Mamba cache table when all the requests are clear
if execute_model_req is None:
self.model_runner.mamba_cache_table.clear()

if (log_graph_compilation or log_cpu_fallbacks) and \
execute_model_req is not None:
from habana_frameworks.torch.hpu.metrics import metric_localcontext
Expand Down