The given huggingface model architecture DeepseekV3ForCausalLM is not supported in TRT-LLM yet
#3 opened 4 days ago
by
wpfnnnns
How to run model on 8xH200
#2 opened about 1 month ago
by
U2hhd24

Remove quantization_config from config.json
#1 opened about 1 month ago
by
alphatozeta