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

[refactor][MiniCPM-o] Consolidate MiniCPM-o 4.5 2-GPU deploy configs and E2E tests (#5458)

Browse Source 
Signed-off-by: y_null <y_null@qq.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
y-nullamy-why-3459Hongsheng LiuGao Han
 authored and GitHub committed 2026-07-30 09:56:19 +08:00
1 parent 1b718f7b15
commit aa5364f705
9 files changed
+132 -137
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/online_serving/minicpmo/README.md
+2 -3
View File
@@ -25,15 +25,14 @@ The deploy config auto-loads via `--omni`.
The default `vllm_omni/deploy/minicpmo_4_5.yaml` keeps all three stages on
logical device 0 with memory budgets of 55%, 22%, and 22%. The profile admits
at most four sequences per stage and bounds startup video profiling to 32
frames per video. For throughput,`minicpmo_4_5_batching.yaml` gives the Thinker
frames per video. For throughput,`minicpmo_4_5_2gpu.yaml` gives the Thinker
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_batching.yaml` | 2 | Recommended continuous-batching layout; Talker and Code2Wav share GPU 1. |
| `minicpmo_4_5_2gpu.yaml` | 2 | Backward-compatible alias for `minicpmo_4_5_batching.yaml`. |
| `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. |