66RING / CritiPrefillLinks
Code repo for "CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs".
☆16Updated last year
Alternatives and similar repositories for CritiPrefill
Users that are interested in CritiPrefill are comparing it to the libraries listed below
Sorting:
- ☆38Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆133Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆154Updated 2 weeks ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆112Updated 8 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆170Updated last year
- ☆155Updated 9 months ago
- Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More☆33Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆63Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆86Updated last year
- ☆132Updated 6 months ago
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆51Updated last month
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- Vocabulary Parallelism☆24Updated 9 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆87Updated 8 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆63Updated last year
- Work in progress.☆75Updated 2 weeks ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆42Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- Cascade Speculative Drafting☆32Updated last year
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆111Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆156Updated 2 months ago
- ☆53Updated last year
- KV cache compression for high-throughput LLM inference☆146Updated 10 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated last week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆126Updated 5 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Updated 8 months ago
- ☆85Updated last month