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

[Bugfix] Fix pin_lora error in TPU executor (#5760)

Browse Source
This commit is contained in:
Woosuk Kwon 2024-06-21 22:25:14 -07:00 committed by GitHub
parent ff9ddbceee
commit 0cbc1d2b4f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/executor/tpu_executor.py
View File

@ -82,6 +82,9 @@ class TPUExecutor(ExecutorBase):
def remove_lora(self, lora_id: int) -> bool: def remove_lora(self, lora_id: int) -> bool:
raise NotImplementedError("LoRA is not implemented for TPU backend.") raise NotImplementedError("LoRA is not implemented for TPU backend.")
def pin_lora(self, lora_id: int) -> bool:
raise NotImplementedError("LoRA is not implemented for TPU backend.")
def list_loras(self) -> Set[int]: def list_loras(self) -> Set[int]:
raise NotImplementedError("LoRA is not implemented for TPU backend.") raise NotImplementedError("LoRA is not implemented for TPU backend.")