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

[Bugfix] fix_small_bug_in_neuron_executor (#4051)

Browse Source
This commit is contained in:
zspo 2024-04-13 22:54:03 +08:00 committed by GitHub
parent ec8e3c695f
commit 0a430b4ae2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/executor/neuron_executor.py
View File

@ -25,6 +25,7 @@ class NeuronExecutor(ExecutorBase):
speculative_config: Optional[SpeculativeConfig],
) -> None:
self.model_config = model_config
self.cache_config = cache_config
assert lora_config is None, "LoRA is not supported for Neuron backend."
self.parallel_config = parallel_config
self.scheduler_config = scheduler_config
@ -43,6 +44,7 @@ class NeuronExecutor(ExecutorBase):
self.parallel_config,
self.scheduler_config,
self.device_config,
self.cache_config,
)
self.driver_worker.init_device()
self.driver_worker.load_model()