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

[CI][MiniCPM-o]MiniCPM-o ACC PERF CI (#5575)

Browse Source 
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
ruirui(rein) yangandamy-why-3459 authored and GitHub committed 2026-08-04 18:46:20 +08:00
1 parent 434c220da1
commit a5eb2a9a87
50 files changed
+1756 -102
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/online_serving/minicpmo/README.md
+1 -1
View File
@@ -25,7 +25,7 @@ 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_batching.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.