SqueezeAILab / SqueezedAttentionLinks
SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference
☆54Updated 10 months ago
Alternatives and similar repositories for SqueezedAttention
Users that are interested in SqueezedAttention are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated 2 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆46Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆66Updated 6 months ago
- LLM Inference with Microscaling Format☆31Updated 10 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- ☆29Updated 10 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆22Updated 11 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆99Updated last week
- ☆52Updated last year
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆54Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆80Updated 11 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated 11 months ago
- ☆18Updated 9 months ago
- ☆43Updated 4 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- ☆38Updated last year
- ☆142Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- ☆60Updated last year
- ☆129Updated 4 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆64Updated 2 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆76Updated 6 months ago
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆23Updated 7 months ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- ☆14Updated last year
- ☆25Updated 2 months ago
- ☆58Updated 10 months ago
- ☆18Updated 6 months ago