RedHatAI
/

Meta-Llama-3.1-8B-Instruct-FP8

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

Resources

View closed (3)

fix: set `clean_up_tokenization_spaces` to `false`

#7 opened 28 days ago by

Not able to use it with TGI

#5 opened over 1 year ago by

Does this model only work on CUDA devices with compute capability >= 9.0 or 8.9/ROCm MI300+?

#4 opened over 1 year ago by

How to fast inference with FP8

#2 opened over 1 year ago by