大佬我用llama.cpp部署qwen时,总是报错怎么办?求解
显示这个:gguf_init_from_file: failed to open GGUF file 'D:\llama\Qwen3-VL-8B-Instruct-abliterated\Qwen3-VL-8B-Instruct-abliterated\ggml-model-q8_0.gguf'
确实,刚发现我的CUDA是12.6版本的。
在安装CUDA12.8时有新问题:
nstalled:
- Nsight Monitor
Not Installed:
- Nsight for Visual Studio 2022
Reason: VS2022 was not found
- Nsight for Visual Studio 2019
Reason: VS2019 was not found
- Integrated Graphics Frame Debugger and Profiler
Reason: see https://developer.nvidia.com/nsight-vstools
- Integrated CUDA Profilers
Reason: see https://developer.nvidia.com/nsight-vstools