machilusZ / FastGen
This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
☆34Updated 7 months ago
Alternatives and similar repositories for FastGen:
Users that are interested in FastGen are comparing it to the libraries listed below
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆33Updated 9 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆58Updated 4 months ago
- ☆50Updated last year
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆85Updated 9 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆44Updated 3 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"