anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[minor, fix] Remove cuda sync on wake_up in AsyncOmni (#4092)

Browse Source 
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
This commit is contained in:
Nguyen Kha Nhat LongandSamit authored and GitHub committed 2026-08-25 03:13:42 +00:00
1 parent f0808c9793
commit bae58f84b8
1 file changed
-2
Download Patch File Download Diff File Expand all files Collapse all files
vllm_omni/entrypoints/async_omni.py
-2
View File
@@ -37,7 +37,6 @@ from vllm_omni.errors import client_error_metadata
from vllm_omni.inputs.data import OmniSamplingParams from vllm_omni.inputs.data import OmniSamplingParams
from vllm_omni.metrics.stats import OrchestratorAggregator as OrchestratorMetrics from vllm_omni.metrics.stats import OrchestratorAggregator as OrchestratorMetrics
from vllm_omni.outputs import OmniRequestOutput from vllm_omni.outputs import OmniRequestOutput
from vllm_omni.platforms import current_omni_platform
if TYPE_CHECKING: if TYPE_CHECKING:
from vllm.inputs.preprocess import InputPreprocessor from vllm.inputs.preprocess import InputPreprocessor
@@ -1447,7 +1446,6 @@ class AsyncOmni(EngineClient, OmniBase):
if ack is not None: if ack is not None:
await self.event_resolver.resolve(ack) await self.event_resolver.resolve(ack)
final_acks.append(ack) final_acks.append(ack)
current_omni_platform.synchronize()
await asyncio.sleep(0.1) await asyncio.sleep(0.1)
return final_acks return final_acks