"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization Paper • 2411.02355 • Published 12 days ago • 44
Llama-3.1 Quantization Collection Neural Magic quantized Llama-3.1 models • 21 items • Updated 3 days ago • 39
FP8 LLMs for vLLM Collection Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated about 1 month ago • 58
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models Paper • 2310.16795 • Published Oct 25, 2023 • 26