docker vllm运行qwen1.5-7b-chat无法部署,报错:Fatal Python error: Bus error Dependencies # 请在此处粘贴依赖情况 # Please paste the dependencies here 运行日志或截图 | Runtime logs or screenshots # 请在此处粘贴运行日志 # Please paste the run log here 👀 1 Liam-Ji commented Mar 25, 2024...
[rank0]: File "~/anaconda3/envs/psp/lib/python3.10/site-packages/vllm/executor/distributed_gpu_executor.py", line 63, in initialize_cache [rank0]: self._run_workers("initialize_cache", [rank0]: File "~/anaconda3/envs/psp/lib/python3.10/site-packages/vllm/executor/multiproc_gpu_execu...
frame #2: c10d::ProcessGroupNCCL::watchdogHandler() + 0x1a0 (0x79bba4baefd0 in /home/ubuntu/miniconda3/envs/meler/lib/python3.11/site-packages/torch/lib/libtorch_cuda.so) frame #3: c10d::ProcessGroupNCCL::ncclCommWatchdog() + 0x10c (0x79bba4bb031c in /home/ubuntu/miniconda3/env...
not define one. INFO 01-17 09:20:08 multiproc_worker_utils.py:126] Killing local vLLM worker processes Fatal Python error: _enter_buffered_busy: could not acquire lock for <_io.BufferedWriter name='<stdout>'> at interpreter shutdown, possibly due to daemon threads Python runtime state: ...
fix bug: #322 #872 Test log: (vllm-boydfd) root:~/projects# python -m vllm.entrypoints.api_server --model /root/WizardLM--WizardCoder-15B-V1.0/ --tensor-parallel-size 8 2023-10-17 19:13:33,431 INFO...
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x96 (0x7f8d14d8df86 in /usr/local/lib/python3.10/dist-packages/torch/lib/libc10.so) frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::string const&) + 0x64 (0x7f8d14d3cd10 in...