Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

docs: avoid unbounded vLLM install guidance

游雁5a37a31462bd
diff --git a/docs/vllm_guide.md b/docs/vllm_guide.md
index d6729640e..6a792a373 100644
--- a/docs/vllm_guide.md
+++ b/docs/vllm_guide.md
@@ -37,7 +37,7 @@
```bash
pip install torch torchaudio
pip install funasr>=1.3.0
-pip install vllm>=0.12.0
+# Install vLLM separately after choosing a version compatible with your NVIDIA driver, CUDA runtime, and PyTorch wheel.
pip install safetensors tiktoken websockets regex fastapi uvicorn python-multipart
cd /path/to/FunASR && pip install -e .
diff --git a/docs/vllm_guide_zh.md b/docs/vllm_guide_zh.md
index 81e44c314..37482780b 100644
--- a/docs/vllm_guide_zh.md
+++ b/docs/vllm_guide_zh.md
@@ -36,7 +36,7 @@
```bash
pip install funasr>=1.3.0
-pip install vllm>=0.12.0
+# 先确认 NVIDIA 驱动、CUDA runtime 和 PyTorch wheel 组合,再固定安装匹配的 vLLM 版本。
pip install safetensors tiktoken websockets regex fastapi uvicorn python-multipart
cd /path/to/FunASR && pip install -e .
diff --git a/docs/vllm_guide_zh_v2.md b/docs/vllm_guide_zh_v2.md
index 0e4a6ea2b..b6cd8f1b6 100644
--- a/docs/vllm_guide_zh_v2.md
+++ b/docs/vllm_guide_zh_v2.md
@@ -37,7 +37,7 @@
```bash
pip install torch torchaudio
pip install funasr>=1.3.0
-pip install vllm>=0.12.0
+# 先确认 NVIDIA 驱动、CUDA runtime 和 PyTorch wheel 组合,再固定安装匹配的 vLLM 版本。
pip install safetensors tiktoken websockets regex fastapi uvicorn python-multipart
cd /path/to/FunASR && pip install -e .
diff --git a/examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md b/examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md
index 53d4e90bf..6e7c3aea6 100644
--- a/examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md
+++ b/examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md
@@ -9,7 +9,7 @@ cd examples/industrial_data_pretraining/fun_asr_nano
# 安装依赖
pip install -r requirements.txt
-pip install vllm>=0.12.0
+# 按主文档选择并安装与当前 NVIDIA 驱动、CUDA runtime 和 PyTorch wheel 匹配的 vLLM 版本。
# 启动服务
CUDA_VISIBLE_DEVICES=0 python serve_realtime_ws.py --port 10095 --language 中文