Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
☆172Oct 13, 2025Updated last year
Alternatives and similar repositories for FlexPrefill
Users that are interested in FlexPrefill are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆288Jul 6, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,231Updated this week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆224Jul 10, 2026Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆316May 1, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Efficient triton implementation of Native Sparse Attention.☆286May 23, 2025Updated last year
- A sparse attention kernel supporting mix sparse patterns☆566Jan 18, 2026Updated 10 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆163Oct 9, 2026Updated last month
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆134Jan 27, 2026Updated 9 months ago
- [ICML 2026] Sparser Block-Sparse Attention via Token Permutation☆33May 22, 2026Updated 5 months ago
- ☆339Jul 10, 2025Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,268Feb 25, 2026Updated 8 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆104Feb 11, 2026Updated 9 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆751Aug 16, 2026Updated 3 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- Fast and memory-efficient exact attention☆23Updated this week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,029Feb 5, 2026Updated 9 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- ☆12Jun 6, 2026Updated 5 months ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆313Dec 1, 2025Updated 11 months ago
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 7 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 4 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆869Mar 6, 2025Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆541Aug 1, 2024Updated 2 years ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆143Nov 26, 2025Updated 11 months ago
- Implementation of "FlashPreill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling"☆57Apr 27, 2026Updated 6 months ago
- ☆255Nov 19, 2025Updated last year
- ☆11Oct 29, 2026Updated 3 weeks ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆229Feb 11, 2026Updated 9 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆55Oct 18, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆407Apr 20, 2024Updated 2 years ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆280Aug 31, 2024Updated 2 years ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆528Aug 24, 2026Updated 2 months ago
- ☆65Apr 26, 2025Updated last year
Are these results useful?