nvidia
/

Llama-3_1-Nemotron-Ultra-253B-v1

Text Generation

Model card Files Files and versions Community

Resources

View closed (2)

Model usage on vLLM fails: `No available memory for the cache blocks` & `Error executing method 'determine_num_available_blocks'`

#8 opened 7 days ago by

benchmark test use vllm ? input/output=500/2000 ？

#6 opened 11 days ago by

FP8 and FP4

#5 opened 11 days ago by

how to reproduce the benchmark score?

#4 opened 16 days ago by

AWQ OR GPTQ Quant

#2 opened 17 days ago by

"ffn_mult": null,

#1 opened 17 days ago by

csabakecskemeti