meta-llama
/

Llama-4-Maverick-17B-128E-Instruct-FP8

Image-Text-to-Text

text-generation-inference

compressed-tensors

Model card Files Files and versions

Resources

View closed (20)

Quantizer: Running into an error with quantization "TypeError: 'dict' object is not callable"

#24 opened 13 days ago by

Support for FP8 + Fused MoE layers in vLLM?

#23 opened 20 days ago by

is it w8a16 or w8a8?

#19 opened 22 days ago by

[request for feedback] faster downloads with xet

#18 opened 24 days ago by