efficient-inference topic

[ICLR 2022] Code for Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation (GLNN)

snap-research

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

SqueezeAILab

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

horseee

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

SqueezeAILab

[NeurIPS'23] Speculative Decoding with Big Little Decoder

kssteven418

Explorations into some recent techniques surrounding speculative decoding

lucidrains

Code for Learning to Zoom and Unzoom (CVPR 2023)

tchittesh

Code for WF-IoT paper 'TinyML Benchmark: Executing Fully Connected Neural Networks on Commodity Microcontrollers'

bharathsudharsan

[ICLR 2020] ”Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference“

VITA-Group

[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang

VITA-Group