"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization Paper • 2411.02355 • Published 5 days ago • 44
Llama-3.1 Quantization Collection Neural Magic quantized Llama-3.1 models • 21 items • Updated Sep 26 • 38
FP8 LLMs for vLLM Collection Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated 24 days ago • 56
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models Paper • 2310.16795 • Published Oct 25, 2023 • 26