Skip to content

GitLab

Unverified Commit 24b65eff authored by Chen Zhang's avatar Chen Zhang Committed by GitHub
Browse files

[BugFix] Spec decode with VLLM_ENABLE_V1_MULTIPROCESSING=0 (#30319) 


Signed-off-by: default avatarChen Zhang <zhangch99@outlook.com>
parent 41b6f920
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
vllm/v1/engine/core_client.py
View file @ 24b65eff
...@@ -268,7 +268,8 @@ class InprocClient(EngineCoreClient): ...@@ -268,7 +268,8 @@ class InprocClient(EngineCoreClient):
self.engine_core = EngineCore(*args, **kwargs) self.engine_core = EngineCore(*args, **kwargs)
def get_output(self) -> EngineCoreOutputs: def get_output(self) -> EngineCoreOutputs:
outputs, _ = self.engine_core.step_fn() outputs, model_executed = self.engine_core.step_fn()
self.engine_core.post_step(model_executed=model_executed)
return outputs and outputs.get(0) or EngineCoreOutputs() return outputs and outputs.get(0) or EngineCoreOutputs()
def get_supported_tasks(self) -> tuple[SupportedTask, ...]: def get_supported_tasks(self) -> tuple[SupportedTask, ...]:
......
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