Sparse-Llama-3.1-2of4 Collection 2:4 sparse versions of Llama-3.1, including transfer learning • 10 items • Updated Dec 18, 2024 • 4
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization Paper • 2411.02355 • Published Nov 4, 2024 • 47
Llama-3.1 Quantization Collection Neural Magic quantized Llama-3.1 models • 22 items • Updated Nov 22, 2024 • 43
FP8 LLMs for vLLM Collection Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17, 2024 • 62
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models Paper • 2310.16795 • Published Oct 25, 2023 • 27