Merge pull request #1640 from Jzz1943/main

support vLLM >=0.11.0 (V1 engine) for better performance

README.md

@@ -152,14 +152,18 @@ python example.py
 ```
 
 #### CosyVoice2 vllm Usage
-If you want to use vllm for inference, please install `vllm==v0.9.0`. Older vllm version do not support CosyVoice2 inference.
+CosyVoice2 now supports **vLLM 0.11.x+ (V1 engine)** and **vLLM 0.9.0 (legacy)**.
+Older vllm version(<0.9.0) do not support CosyVoice2 inference, and versions in between (e.g., 0.10.x) are not tested.
 
 Notice that `vllm==v0.9.0` has a lot of specific requirements, for example `torch==2.7.0`. You can create a new env to in case your hardward do not support vllm and old env is corrupted.
 
 ``` sh
 conda create -n cosyvoice_vllm --clone cosyvoice
 conda activate cosyvoice_vllm
+# for vllm==0.9.0
 pip install vllm==v0.9.0 transformers==4.51.3 numpy==1.26.4 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+# for vllm>=0.11.0
+pip install vllm==v0.11.0 transformers==4.57.1 numpy==1.26.4 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
 python vllm_example.py
 ```
 

cosyvoice/vllm/cosyvoice2.py

@@ -23,6 +23,15 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 """Inference-only Qwen2 model compatible with HuggingFace weights."""
+from typing import Optional
+from packaging.version import parse as vparse
+import vllm
+
+# vLLM-0.11.0+ only support V1 engine
+VLLM_V1_ENGINE_ONLY: bool = vparse(vllm.__version__) >= vparse("0.11.0")
+if VLLM_V1_ENGINE_ONLY:
+    from vllm.v1.sample.metadata import SamplingMetadata
+
 from vllm.model_executor.models.qwen2 import *
 
 
@@ -87,10 +96,14 @@ class CosyVoice2ForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
     def compute_logits(
         self,
         hidden_states: torch.Tensor,
-        sampling_metadata: SamplingMetadata,
+        sampling_metadata: Optional[SamplingMetadata] = None,
     ) -> Optional[torch.Tensor]:
-        logits = self.logits_processor(self.lm_head, hidden_states,
-                                       sampling_metadata, self.lm_head.bias)
+        if VLLM_V1_ENGINE_ONLY:
+            logits = self.logits_processor(self.lm_head, hidden_states, 
+                                           self.lm_head.bias)
+        else:
+            logits = self.logits_processor(self.lm_head, hidden_states,
+                                           sampling_metadata, self.lm_head.bias)
         return logits
 
     def load_weights(self, weights: Iterable[tuple[str,