lai-serena
lai-serena
这个是没解决办法了吗？官方都不回了..
paddle 2.6版本应该是不支持的，退回paddle 2.5版本
> @lai-serena To test the FPS of the model, you should use the https://github.com/open-mmlab/mmdetection/blob/3.x/tools/analysis_tools/benchmark.py script. Your testing method is not correct.  thanks for answer my question!This is the...
> @lvhan028 感觉这个问题是个大bug，vl的模型，我用着经常会遇到这个偶发卡住的问题。没有报错，就是hang住不返回。看着像是accelerate和lmdeploy的集合通信互相死锁了，因为请求是异步发出的，vit的推理和llm的推理实际上是流水线重叠的。trace的日志： > > ```shell > -- Stack for thread 23201439544896 --- > File "/usr/lib/python3.10/threading.py", line 973, in _bootstrap > self._bootstrap_inner() > File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner >...
> I had the same issue. Please try vllm>=0.7.0 instead. it's work! thank you
同问