frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Perf] Optimize _update_states for GPU model runner (#16910)

Browse Source 
Signed-off-by: snowcharm <snowcharmqq@gmail.com>
This commit is contained in:
SnowCharm
2025-04-22 14:01:54 +08:00
committed by GitHub
parent 3097ce3a32
commit a114bf20a3
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -454,7 +454,7 @@ class GPUModelRunner(LoRAModelRunnerMixin):
# Add the new or resumed requests to the persistent batch.
# The smaller empty indices are filled first.
removed_req_indices = sorted(removed_req_indices, reverse=True)
removed_req_indices.sort(reverse=True)
for req_id in req_ids_to_add:
req_state = self.requests[req_id]
if removed_req_indices: