dongkuang

install vllm,but show CUDA runtime is found,please help me,thank you!

1

### Discussed in https://github.com/vllm-project/vllm/discussions/329 Originally posted by **dongkuang** July 2, 2023 running build_py running build_ext No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda-11.8' Traceback (most recent call last): File "/tmp/pip-build-env-1bv509_l/overlay/lib/python3.8/site-packages/setuptools/command/editable_wheel.py", line...

RuntimeError: CUDA error

3

Please help me ! I run it in Jetson orin 64G,is aarch64 cuda_11.8.r11.8,pytorch2.0.0,show error after click "Sample" RuntimeError: CUDA error: invalid device function Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions....

Nvidia-fabricmanager failed to start with “NV_WARN_NOTHING_TO_DO”

5

[Uploading NVlinkError-fabricmanager-en1.docx…]() I have 1 NVLink device to connect 2 nvidia A40 graphics cards, used ubuntu20.04 system, downloaded and installed nvidia-driver-local-repo-ubuntu2004-515.105.01_1.0-1_ amd64 .deb driver from the official website, and then...

在与excel交互时，数据经常查不全，如有15条数据，就展示12条，怎么改提示词，都是12条，但时而12条数据还不是同一批，说明数据向量化是成功的，就是每次调用时调不全，不知道为什么？大家有遇到过吗？我用的是qwen110b的模型测试的

ltx-video-0.9.1 The pointed commit hash does not exist

**Which OS are you using?** - OS: Ubuntu nano /home/用户名/Whisper-WebUI/modules/diarize/diarize_pipeline.py 找到segments = self.model(audio_data, min_speakers=min_speakers, max_speakers=max_speakers)这行，把所在函数下面代码替换成： annotation = None if hasattr(segments, "speaker_diarization"): candidate = getattr(segments, "speaker_diarization") if hasattr(candidate, "itertracks"): annotation =...