 quantu
|
3298d6f3e3
readme
|
8 月之前 |
 lyuxiang.lx
|
f21c4764ec
fix bug
|
8 月之前 |
|
lyuxiang.lx
|
927addadd8
fix lint
|
8 月之前 |
|
lyuxiang.lx
|
a051a09ba4
remove unncessary code
|
8 月之前 |
|
lyuxiang.lx
|
0c65d3c7ab
use automodel
|
8 月之前 |
|
lyuxiang.lx
|
56d9876037
fix bug
|
8 月之前 |
|
lyuxiang.lx
|
b35ece675b
dit need higher trt version
|
8 月之前 |
|
lyuxiang.lx
|
59f02cb85d
add vllm example
|
8 月之前 |
|
lyuxiang.lx
|
b4dd67a8af
add cosyvoice3 vllm example
|
8 月之前 |
|
lyuxiang.lx
|
bfa835a74b
add cosyvoice3 inference code
|
8 月之前 |
|
lyuxiang.lx
|
622a3a19b0
use wav file rather than tensor
|
8 月之前 |
|
lyuxiang.lx
|
d985100326
Merge branch 'main' into dev/lyuxiang.lx
|
8 月之前 |
 zhongze.jiang
|
6816fc6a6f
support vLLM >=0.11.0 (V1 engine only)
|
9 月之前 |
 김의진
|
e8bf717333
Fix: generate token2wav_request_id from cosyvoice2
|
10 月之前 |
|
김의진
|
fa2781405f
Revert "fix triton token2wav model cache thread unsafety"
|
10 月之前 |
|
김의진
|
cd26dd1932
fix triton token2wav model cache thread unsafety
|
10 月之前 |
|
Xiang Lyu
|
6e01309e01
Merge pull request #1598 from yuekaizhang/streaming
|
10 月之前 |
 yuekaiz
|
1fc8435146
add disaggregated deployment
|
10 月之前 |
|
yuekaiz
|
a224be6117
fix lint
|
10 月之前 |
 yuekaiz
|
33aee03ed5
fix lint
|
10 月之前 |
 root
|
8811e9f33a
fix white space
|
10 月之前 |
|
root
|
807bb6ee0b
add dit results
|
10 月之前 |
|
root
|
aceede59ba
fix bug
|
10 月之前 |
|
root
|
7cbd490253
add docker compose for streaming tts
|
10 月之前 |
|
root
|
a019a2504e
clean code
|
10 月之前 |
|
root
|
f186ec3338
clean code
|
10 月之前 |
|
root
|
988d395162
mark multi client
|
10 月之前 |
|
lyuxiang.lx
|
4d60ff6abc
Merge branch 'main' of github.com:FunAudioLLM/CosyVoice into main
|
11 月之前 |
|
lyuxiang.lx
|
be005c825f
fix vllm transformer version bug
|
11 月之前 |
|
root
|
79116ac32e
remove cache router
|
11 月之前 |
