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

[Bugfix] Restore the async PP sampled-token broadcast in the AR runner (#7393)

Browse Source 
Signed-off-by: Deep Shah <deep@socratic.co>
This commit is contained in:
Deep Shah authored and GitHub committed 2026-09-14 20:41:03 -07:00
1 parent 85da943391
commit 5761ad5516
3 files changed
+333 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/examples/online_serving/qwen3_omni.md
+2 -2
View File
@@ -23,8 +23,8 @@ some GPUs.
Asynchronous chunk streaming is **enabled by default** within the bundled configuration.
For Thinker pipeline parallelism, configure `pipeline_parallel_size` and `devices`
on the Thinker stage and set `async_scheduling: false`. Keep Talker and Code2Wav
at `pipeline_parallel_size: 1`. Audio chunk streaming can remain enabled.
on the Thinker stage. Keep Talker and Code2Wav at `pipeline_parallel_size: 1`. The
default asynchronous scheduling and audio chunk streaming can remain enabled.
To explicitly utilize a custom deployment YAML, specify the configuration path:
```bash