Matriv-org
Results
2
comments of
Matriv-org
Hi, I've the exact same issues, change from torch 2.4.0 with CUDA 12.4 to torch 2.3.1 with CUDA 12.1 didn't change anything. Did you find the solution ? Thanks in...
I'm doing something wrong or support isn't released atm ? I'm using VLLM 0.8.6dev RTX 5090, Torch 2.7, cu128, bitsandbytes 0.45.5 ``` "vllm", "serve", "unsloth/Qwen3-30B-A3B-bnb-4bit", "--max-model-len", "2048", "--enable-reasoning", "--reasoning-parser", "deepseek_r1",...