Skip to content

GitLab

Unverified Commit 0a430b4a authored by zspo's avatar zspo Committed by GitHub
Browse files

[Bugfix] fix_small_bug_in_neuron_executor (#4051)

parent ec8e3c69
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/executor/neuron_executor.py
View file @ 0a430b4a
...@@ -25,6 +25,7 @@ class NeuronExecutor(ExecutorBase): ...@@ -25,6 +25,7 @@ class NeuronExecutor(ExecutorBase):
speculative_config: Optional[SpeculativeConfig], speculative_config: Optional[SpeculativeConfig],
) -> None: ) -> None:
self.model_config = model_config self.model_config = model_config
self.cache_config = cache_config
assert lora_config is None, "LoRA is not supported for Neuron backend." assert lora_config is None, "LoRA is not supported for Neuron backend."
self.parallel_config = parallel_config self.parallel_config = parallel_config
self.scheduler_config = scheduler_config self.scheduler_config = scheduler_config
...@@ -43,6 +44,7 @@ class NeuronExecutor(ExecutorBase): ...@@ -43,6 +44,7 @@ class NeuronExecutor(ExecutorBase):
self.parallel_config, self.parallel_config,
self.scheduler_config, self.scheduler_config,
self.device_config, self.device_config,
self.cache_config,
) )
self.driver_worker.init_device() self.driver_worker.init_device()
self.driver_worker.load_model() self.driver_worker.load_model()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment