SalesforceAIResearch / ThinKLinks
ThinK: Thinner Key Cache by Query-Driven Pruning
☆24Updated 9 months ago
Alternatives and similar repositories for ThinK
Users that are interested in ThinK are comparing it to the libraries listed below
Sorting:
- A Sober Look at Language Model Reasoning☆89Updated last week
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆67Updated 4 months ago
- [ICML 2024] SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models☆21Updated last year
- ☆108Updated 2 months ago
- ☆23Updated last year
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆110Updated last year
- ☆76Updated last year
- ☆142Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆142Updated 4 months ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆99Updated 5 months ago
- Codes for Merging Large Language Models☆33Updated last year
- ☆26Updated this week
- ☆39Updated last year
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆82Updated 5 months ago
- Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation, ICML 2024☆22Updated last year
- ☆45Updated 2 months ago
- Implementation of CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation☆24Updated 9 months ago
- [ICLR 2025🔥] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models☆25Updated 4 months ago
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆50Updated last year
- RL with Experience Replay☆49Updated 4 months ago
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆45Updated 7 months ago
- LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning☆36Updated last year
- ☆120Updated 5 months ago
- ☆62Updated 2 years ago
- [AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models☆63Updated last year
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆40Updated last year
- This pytorch package implements PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance (ICML 2022).☆46Updated 3 years ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆189Updated 5 months ago
- ☆10Updated last year
- AnchorAttention: Improved attention for LLMs long-context training☆213Updated 10 months ago