deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

add contributor info

Browse Source
This commit is contained in:
lyuxiang.lx
2025-08-05 11:15:42 +08:00
parent 1850e2a56e
commit 05bdf4c769
4 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -29,6 +29,10 @@
## Roadmap ## Roadmap
- [x] 2025/08
- [x] Thanks to the contribution from NVIDIA Yuekai Zhang, add triton trtllm runtime support
- [x] 2025/07 - [x] 2025/07
- [x] release cosyvoice 3.0 eval set - [x] release cosyvoice 3.0 eval set

2
runtime/triton_trtllm/Dockerfile.server
View File

@@ -1,4 +1,6 @@
FROM nvcr.io/nvidia/tritonserver:25.06-trtllm-python-py3 FROM nvcr.io/nvidia/tritonserver:25.06-trtllm-python-py3
LABEL maintainer="zhangyuekai@foxmail.com"
RUN apt-get update && apt-get install -y cmake RUN apt-get update && apt-get install -y cmake
RUN git clone https://github.com/pytorch/audio.git && cd audio && git checkout c670ad8 && PATH=/usr/local/cuda/bin:$PATH python3 setup.py develop RUN git clone https://github.com/pytorch/audio.git && cd audio && git checkout c670ad8 && PATH=/usr/local/cuda/bin:$PATH python3 setup.py develop
COPY ./requirements.txt /workspace/requirements.txt COPY ./requirements.txt /workspace/requirements.txt

2
runtime/triton_trtllm/README.md
View File

@@ -1,5 +1,7 @@
## Best Practices for Serving CosyVoice with NVIDIA Triton Inference Server ## Best Practices for Serving CosyVoice with NVIDIA Triton Inference Server
Thanks to the contribution from NVIDIA Yuekai Zhang.
### Quick Start ### Quick Start
Launch the service directly with Docker Compose: Launch the service directly with Docker Compose:
```sh ```sh

9
runtime/triton_trtllm/run.sh
View File

@@ -1,4 +1,5 @@
#!/bin/bash
# Copyright (c) 2025 NVIDIA (authors: Yuekai Zhang)
export CUDA_VISIBLE_DEVICES=0 export CUDA_VISIBLE_DEVICES=0
cosyvoice_path=/workspace/CosyVoice cosyvoice_path=/workspace/CosyVoice
export PYTHONPATH=${cosyvoice_path}:$PYTHONPATH export PYTHONPATH=${cosyvoice_path}:$PYTHONPATH
@@ -24,8 +25,8 @@ fi
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
echo "Downloading CosyVoice2-0.5B" echo "Downloading CosyVoice2-0.5B"
huggingface-cli download --local-dir $huggingface_model_local_dir yuekai/cosyvoice2_llm huggingface-cli download --local-dir $huggingface_model_local_dir yuekai/cosyvoice2_llm
modelscope download --model iic/CosyVoice2-0.5B --local_dir $model_scope_model_local_dir modelscope download --model iic/CosyVoice2-0.5B --local_dir $model_scope_model_local_dir
fi fi
@@ -67,7 +68,7 @@ if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
BLS_INSTANCE_NUM=4 BLS_INSTANCE_NUM=4
TRITON_MAX_BATCH_SIZE=16 TRITON_MAX_BATCH_SIZE=16
DECOUPLED_MODE=False DECOUPLED_MODE=False
python3 scripts/fill_template.py -i ${model_repo}/token2wav/config.pbtxt model_dir:${MODEL_DIR},triton_max_batch_size:${TRITON_MAX_BATCH_SIZE},max_queue_delay_microseconds:${MAX_QUEUE_DELAY_MICROSECONDS} python3 scripts/fill_template.py -i ${model_repo}/token2wav/config.pbtxt model_dir:${MODEL_DIR},triton_max_batch_size:${TRITON_MAX_BATCH_SIZE},max_queue_delay_microseconds:${MAX_QUEUE_DELAY_MICROSECONDS}
python3 scripts/fill_template.py -i ${model_repo}/audio_tokenizer/config.pbtxt model_dir:${MODEL_DIR},triton_max_batch_size:${TRITON_MAX_BATCH_SIZE},max_queue_delay_microseconds:${MAX_QUEUE_DELAY_MICROSECONDS} python3 scripts/fill_template.py -i ${model_repo}/audio_tokenizer/config.pbtxt model_dir:${MODEL_DIR},triton_max_batch_size:${TRITON_MAX_BATCH_SIZE},max_queue_delay_microseconds:${MAX_QUEUE_DELAY_MICROSECONDS}
python3 scripts/fill_template.py -i ${model_repo}/${cosyvoice2_dir}/config.pbtxt model_dir:${MODEL_DIR},bls_instance_num:${BLS_INSTANCE_NUM},llm_tokenizer_dir:${LLM_TOKENIZER_DIR},triton_max_batch_size:${TRITON_MAX_BATCH_SIZE},decoupled_mode:${DECOUPLED_MODE},max_queue_delay_microseconds:${MAX_QUEUE_DELAY_MICROSECONDS} python3 scripts/fill_template.py -i ${model_repo}/${cosyvoice2_dir}/config.pbtxt model_dir:${MODEL_DIR},bls_instance_num:${BLS_INSTANCE_NUM},llm_tokenizer_dir:${LLM_TOKENIZER_DIR},triton_max_batch_size:${TRITON_MAX_BATCH_SIZE},decoupled_mode:${DECOUPLED_MODE},max_queue_delay_microseconds:${MAX_QUEUE_DELAY_MICROSECONDS}