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

Update pre-commit hooks (#12475)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-01-28 00:23:08 +00:00
committed by GitHub
parent 6116ca8cd7
commit 823ab79633
64 changed files with 322 additions and 288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu_model_runner.py
View File

@@ -205,7 +205,7 @@ class GPUModelRunner:
def _update_states(self, scheduler_output: "SchedulerOutput") -> None:
# Remove stopped requests from the cached states.
# Keep the states of the pre-empted requests.
# Keep the states of the preempted requests.
for req_id in scheduler_output.finished_req_ids:
self.requests.pop(req_id, None)
self.encoder_cache.pop(req_id, None)