@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 0cbc1d2b4f
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 23:15 UTC

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

Woosuk Kwon committed Jun 21, 2024 at 22:25 UTC 0cbc1d2b4ff9e3afa32ffd2d5d308c136c2d15e3
1 file changed +3
vllm/executor/tpu_executor.py
+3
@@ -82,6 +82,9 @@ class TPUExecutor(ExecutorBase):
82 def remove_lora(self, lora_id: int) -> bool:
83 raise NotImplementedError("LoRA is not implemented for TPU backend.")
84
85 + def pin_lora(self, lora_id: int) -> bool:
86 + raise NotImplementedError("LoRA is not implemented for TPU backend.")
87 +
88 def list_loras(self) -> Set[int]:
89 raise NotImplementedError("LoRA is not implemented for TPU backend.")
90