[Bugfix][MiniCPM-o] Serve native duplex from shipping YAMLs and fence… (#6619)

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
amy-why-3459 authored and GitHub committed 2026-08-26 10:56:51 +08:00
1 parent 7ae15c74c8
commit 5de6f7c37a
19 files changed
+178 -115

No files matched your search

+7 -5
View File
@@ -32,12 +32,14 @@ GPU 0 (90%) and colocates the Talker (55%) and Code2Wav (35%) on GPU 1. That
profile admits at most four concurrent sequences per stage.
| deploy config | GPUs | Notes |
|---|---|---|
| --- | --- | --- |
| `minicpmo_4_5.yaml` (default) | 1 | Memory-constrained compatibility layout. |
| `minicpmo_4_5_2gpu.yaml` | 2 | Recommended continuous-batching layout; Talker and Code2Wav share GPU 1. |
| `minicpmo_4_5_3gpu.yaml` | 3 | One GPU per stage. |
| `minicpmo_4_5_8x4090.yaml` | 8 | Full 8x4090 layout. |
| `minicpmo_4_5_duplex.yaml` | 1 | Experimental native full-duplex overlay. |
Every profile sets `session_mode: duplex`, so native full-duplex is served
from the same process as `/v1/chat/completions`.
The split pipeline preserves native-duplex epoch/turn identity, segment text,
turn completion, reference voice, and terminal-audio metadata through
@@ -55,8 +57,8 @@ vllm-omni serve openbmb/MiniCPM-o-4_5 \
```
For local ModelScope checkpoints, replace `openbmb/MiniCPM-o-4_5` with the
checkpoint path. To start the experimental native duplex backend, use
`vllm_omni/deploy/minicpmo_4_5_duplex.yaml`.
checkpoint path. For native full-duplex, connect `/v1/realtime?duplex=1` on
this same server.
### Per-stage overrides
@@ -145,7 +147,7 @@ assistant template, so it is not an apples-to-apples accuracy run.
## Run the Realtime duplex CLI demo
After the duplex backend is running, stream one WAV through the Realtime
After the server is running, stream one WAV through the Realtime
WebSocket endpoint:
```bash