xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-22 08:47:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Perf] Dont create unnecessary pooling params (#22876)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
This commit is contained in:
Lucas Wilkinson 2025-08-14 08:28:09 -04:00 committed by GitHub
parent 540d54ca8d
commit 829b9a62d0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/v1/worker/gpu_model_runner.py
View File

@ -341,13 +341,13 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
model_kwargs = dict[str, Any]()
num_reqs = self.input_batch.num_reqs
pooling_params = self.input_batch.pooling_metadata.pooling_params
num_pooling_reqs = len(pooling_params)
num_pooling_reqs = len(self.input_batch.pooling_params)
if num_pooling_reqs == 0:
return model_kwargs
pooling_params = self.input_batch.pooling_metadata.pooling_params
assert num_pooling_reqs == num_reqs
token_type_id_requests = dict[int, Any]()