xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-28 19:07:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
Chen Zhang 2025-12-18 11:47:56 -08:00 committed by GitHub
parent 41b6f9200f
commit 24b65eff0d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/v1/engine/core_client.py
View File

@ -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, ...]: