BitNet a4.8: 4-bit Activations for 1-bit LLMs
Paper
•
2411.04965
•
Published
•
64
quantize
-
-
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
Paper • 2411.02355 • Published • 46 -
Ultra-Sparse Memory Network
Paper • 2411.12364 • Published • 19 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 105 -
Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers
Paper • 2410.14072 • Published -
FoPru: Focal Pruning for Efficient Large Vision-Language Models
Paper • 2411.14164 • Published -
NVILA: Efficient Frontier Visual Language Models
Paper • 2412.04468 • Published • 57