xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-01 18:51:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][TPU] Fix TPU sampler output (#5978)

Browse Source
This commit is contained in:
Woosuk Kwon 2024-06-28 18:14:16 -07:00 committed by GitHub
parent 7041de4384
commit 54814fd85b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/worker/tpu_worker.py
View File

@ -215,7 +215,7 @@ class TPUWorker(LoraNotSupportedWorkerBase):
assert len(seq_group_metadata_list) > 0
output = self.model_runner.execute_model(seq_group_metadata_list,
self.tpu_cache)
return [output]
return output
def cache_swap(
self,