Hugging Face's logo

neuralmagic
/
Mistral-Nemo-Instruct-2407-FP8

Text Generation
Transformers
Safetensors
English
mistral
fp8
vllm
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
3
New discussion

7900xtx torch._scaled_mm is only supported on CUDA devices with compute capability >= 9.0 or 8.9, or ROCm MI300+

1
#3 opened 21 days ago by aaaaaaaaaasdf