model: Minicpmo#3023
Conversation
1764685 to
de11d37
Compare
bc33318 to
78f5175
Compare
|
I think we should add test |
87f83d4 to
d00dc4d
Compare
There was a problem hiding this comment.
Can we directly move audio related test into TestMinicpmoServer?
|
LGTM,after ci passes and unit test related issues have been solved, this PR can be merged. cc @zhaochenyang20 and plz paste MMMU benchmark result here~ @mickqian |
|
FYI, tts model in current Minicpmo is not used, as well as streaming audio embedding |
|
|
@yizhang2077 wait for yi's approval! |
|
great!let me rerun the CI and merge it asap |
|
@zhaochenyang20 we may need contributor to support audio benchmark |
|
great work1! |
merrymercy
left a comment
There was a problem hiding this comment.
Please move all model-specific files under python/sglang/srt/managers/multimodal_processors to python/sglang/srt/models/
|
Hi @mickqian , since you have added WhisperAttention and WhisperEncoder in the current PR, I am wondering that do you have any plan to support Whisper model in SGLang? Thanks! |
For new model support, could you add my wechat 18015766633 |
Motivation
Support openbmb/MiniCPM-o-2_6
Modifications
Checklist