add mimo-audio, Qwen-TTS model backbone quantization #1810
WeiweiZhang1
merged
16 commits into
main
from
support_audio_model_quantization
WeiweiZhang1
changed the title 
n1ck-guo
commented
on 2026-05-13
n1ck-guo
commented
on 2026-05-13
add audio model text backbone quantization
1ce6a44b
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
5e7093ef
refine mimo quant, fix comments
6b846c9c
address PR review: consolidate audio processors, extract shared audio…
71247161
[pre-commit.ci] auto fixes from pre-commit.com hooks
71fd388f
refine stable-audio pipe
0dd3f59b
[pre-commit.ci] auto fixes from pre-commit.com hooks
d525bcbb
add CI tests
f43ebf40
[pre-commit.ci] auto fixes from pre-commit.com hooks
6c13d332
fix CI
bedc4438
Merge origin/main into support_audio_model_quantization
3f924f4f
test: add CPU dummy-model UTs for qwen3_tts audio flow
daa8cb12
Revert "test: add CPU dummy-model UTs for qwen3_tts audio flow"
5dbb754b
Merge origin/main and resolve conflicts
d57fcdea
fix ci
12039717
Merge branch 'main' into support_audio_model_quantization
5c2c34fe
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
Login to write a write a comment.
Login via GitHub