FP8 LLMs for vLLM Collection Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! β’ 44 items β’ Updated Oct 17, 2024 β’ 74
view article Article Finally, a Replacement for BERT: Introducing ModernBERT By bclavie and 14 others β’ Dec 19, 2024 β’ 646