biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-09-06 16:15:18 -07:00
committed by GitHub
parent 848562bd49
commit 4172235ab7
46 changed files with 10 additions and 5462 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/engine/arg_utils.py
View File

@@ -419,8 +419,6 @@ class EngineArgs:
scheduling_policy: SchedulerPolicy = SchedulerConfig.policy
scheduler_cls: Union[str, Type[object]] = SchedulerConfig.scheduler_cls
override_neuron_config: dict[str, Any] = \
get_field(ModelConfig, "override_neuron_config")
override_pooler_config: Optional[Union[dict, PoolerConfig]] = \
ModelConfig.override_pooler_config
compilation_config: CompilationConfig = \
@@ -561,8 +559,6 @@ class EngineArgs:
help=model_kwargs["hf_token"]["help"])
model_group.add_argument("--hf-overrides",
**model_kwargs["hf_overrides"])
model_group.add_argument("--override-neuron-config",
**model_kwargs["override_neuron_config"])
model_group.add_argument("--override-pooler-config",
**model_kwargs["override_pooler_config"])
model_group.add_argument("--logits-processor-pattern",
@@ -992,7 +988,6 @@ class EngineArgs:
mm_processor_kwargs=self.mm_processor_kwargs,
mm_processor_cache_gb=self.mm_processor_cache_gb,
mm_encoder_tp_mode=self.mm_encoder_tp_mode,
override_neuron_config=self.override_neuron_config,
override_pooler_config=self.override_pooler_config,
logits_processor_pattern=self.logits_processor_pattern,
generation_config=self.generation_config,