torch 2.10.0+cu130
torchaudio 2.10.0+cu130
torchvision 0.25.0+cu130
vllm 0.16.0rc2.dev130+g386bfe5d0.cu130
vllm serve nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
–served-model-name model --max-num-seqs 256 --tensor-parallel-size 1
–max-model-len 262144 --port 8000 --trust-remote-code
–enable-auto-tool-choice --tool-call-parser qwen3_coder
–reasoning-parser-plugin nano_v3_reasoning_parser.py
–reasoning-parser nano_v3 --kv-cache-dtype fp8
attaching the flashinfer logging from a misaligned address error (responsible for one crash) and the much more common illegal instruction parameter version (responsible for the second)
flashinferlogs.tar.gz (1007.8 KB)