xujian_tbup

@canghongjian @dalong2hongmei Hello, have you solved it? I have also experienced vllm-v0.1.3 hanging issues twice, and it's like a deadlock problem. It's hard to locate code position.

Mine might be a different problem. I've reproduced it. If there are many interrupt requests to abort, the vllm service will not pass the pressure test because fall into an...

> Mine might be a different problem. I've reproduced it. If there are many interrupt requests to abort, the vllm service will not pass the pressure test because fall into...

@launchauto @michuanhaohao me too, but I run it with precision O0. Did you run with the O0 precision? [log_rank0.txt](https://github.com/SwinTransformer/Transformer-SSL/files/8021405/log_rank0.txt)

same issue! and rebuilt. images: openmmlab/lmdeploy:v0.6.0-cu11 nvidia-smi: Driver Version: 525.147.05 CUDA Version: 12.0

> same issue! and rebuilt. images: openmmlab/lmdeploy:v0.6.0-cu11 > > nvidia-smi: Driver Version: 525.147.05 CUDA Version: 12.0 @lvhan028 I meet this error on Grid VGPU A800. VGPU is not support? But...