 禾息
|
369f3c2c18
Update estimator count retrieval and memory pool limit in CosyVoice
|
hai 1 ano |
|
禾息
|
7f4c9a2c64
Refactor CosyVoice inference methods to streamline CUDA stream management
|
hai 1 ano |
|
禾息
|
fd9b7d45e2
Fix logging indentation in CosyVoice TTS method for improved clarity
|
hai 1 ano |
|
禾息
|
62e04e8856
Enhance CosyVoice with CUDA stream management and estimator handling
|
hai 1 ano |
 雾聪
|
96950745a6
Revert "mv AsyncLLMEngine init to CosyVoice2"
|
hai 1 ano |
|
雾聪
|
9b3f351496
mv AsyncLLMEngine init to CosyVoice2
|
hai 1 ano |
 Yabin Li
|
00b454cf30
Merge pull request #1053 from qi-hua/dev/use_vllm
|
hai 1 ano |
 qihua
|
c0f6a474f3
fix(async_cosyvoice): 恢复原本文本令牌处理逻辑
|
hai 1 ano |
|
qihua
|
ab5b8eb160
refactor(llm): 重构 vLLM 推理任务处理方式，支持多任务处理
|
hai 1 ano |
|
qihua
|
b4fe05d466
docs: 添加speed_test.ipynb文件
|
hai 1 ano |
|
qihua
|
a1314e573a
chore: 新增 requirements_vllm.txt 文件，指定VLLM 模型所需的依赖
|
hai 1 ano |
|
qihua
|
2fbeba50ae
refactor(llm): 移除未使用的异步推理方法
|
hai 1 ano |
|
qihua
|
d4d187bd8c
refactor(llm): 重构 VLLM 推理方式
|
hai 1 ano |
|
qihua
|
90b666ea20
初步合并vllm支持，异步推理的通道处理还存在bug
|
hai 1 ano |
 Xiang Lyu
|
fd45708e4b
Merge pull request #977 from hanasay/main
|
hai 1 ano |
 hanasay
|
296ed4f526
Convert audio to mono while extract speech token
|
hai 1 ano |
|
Xiang Lyu
|
95e99e0417
Merge pull request #940 from c4fun/fastapi-cosyvoice2
|
hai 1 ano |
 c4fun
|
ba6d8c07ba
revert the main function to original and only preserve the inference endpoint
|
hai 1 ano |
|
Xiang Lyu
|
da3f129977
Merge pull request #936 from huyyxy/main
|
hai 1 ano |
|
c4fun
|
2889c25863
supports and defaultly supports cosyvoice2 in fastapi server
|
hai 1 ano |
 huyyxy
|
aa65200713
feat(docker): update CUDA base image to 12.4.1 for TensorRT support
|
hai 1 ano |
|
Xiang Lyu
|
86e26f54c7
Merge pull request #930 from sd0ric4/main
|
hai 1 ano |
 sd0ric4
|
f1c214377c
fix: add POST endpoints to resolve browser error about GET request with body
|
hai 1 ano |
|
Xiang Lyu
|
369ea80bd4
Merge pull request #926 from Vinkle-hzt/main
|
hai 1 ano |
 huzetao.hzt
|
69518b2bde
fix bistream extra token
|
hai 1 ano |
|
Xiang Lyu
|
276cfa02b6
Merge pull request #925 from FunAudioLLM/dev/lyuxiang.lx
|
hai 1 ano |
|
lyuxiang.lx
|
190840b8dc
fix pitch computation
|
hai 1 ano |
|
lyuxiang.lx
|
c6c3f27ecc
fix typo
|
hai 1 ano |
|
Xiang Lyu
|
49761d2474
Merge pull request #924 from FunAudioLLM/dev/lyuxiang.lx
|
hai 1 ano |
|
lyuxiang.lx
|
07e477519b
add llm bistream
|
hai 1 ano |
