krafton-ai / lexicoLinks
KV cache compression via sparse coding
☆12Updated 3 months ago
Alternatives and similar repositories for lexico
Users that are interested in lexico are comparing it to the libraries listed below
Sorting:
- ☆14Updated 11 months ago
- Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)☆12Updated 2 months ago
- 2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models (WWW 2025)☆10Updated 4 months ago
- ☆15Updated 9 months ago
- ☆11Updated last month
- Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"☆13Updated 5 months ago
- ☆20Updated last month
- ☆21Updated 7 months ago
- Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆21Updated 3 months ago
- ☆10Updated 9 months ago
- A specialized RWKV-7 model for Othello(a.k.a. Reversi) that predicts legal moves, evaluates positions, and performs in-context search. It…☆42Updated 7 months ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆15Updated 8 months ago
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆104Updated last week
- Official Implementation of FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation☆22Updated 3 months ago
- ☆57Updated last month
- The Official Code Repo for EgoOrientBench [CVPR25]☆13Updated 2 weeks ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated 2 months ago
- Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More☆33Updated 3 months ago
- Geometric-Mean Policy Optimization☆68Updated last month
- ☆26Updated last month
- Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents☆18Updated 8 months ago
- Code for I-RAVEN-X generation and experiments☆15Updated 3 months ago
- Code for Heima☆52Updated 4 months ago
- The official code implementation for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing"☆45Updated last week
- ☆10Updated 11 months ago
- ☆18Updated 5 months ago
- JudgeLRM: Large Reasoning Models as a Judge☆35Updated 4 months ago
- ☆32Updated last month
- ☆15Updated 9 months ago
- ☆20Updated this week