[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
☆1,227Apr 8, 2026Updated 4 months ago
Alternatives and similar repositories for MInference
Users that are interested in MInference 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 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆403Jul 10, 2025Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆430Nov 20, 2025Updated 9 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆854Mar 6, 2025Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆171Oct 13, 2025Updated 10 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆331Jul 10, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,262Updated this week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆532Aug 1, 2024Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆974Mar 29, 2026Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,137Sep 4, 2024Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- A sparse attention kernel supporting mix sparse patterns☆548Jan 18, 2026Updated 7 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆281Aug 31, 2024Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆433Aug 13, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆736Aug 16, 2026Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆157Dec 4, 2024Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆313May 1, 2025Updated last year
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆450Oct 16, 2024Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,768Jun 25, 2024Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,342Mar 6, 2025Updated last year
- ☆65Apr 26, 2025Updated last year
- LLM KV cache compression made easy☆1,195Aug 18, 2026Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,405Updated this week
- 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.
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,245Updated this week
- Ring attention implementation with flash attention☆1,049Sep 10, 2025Updated 11 months ago
- A low-latency & high-throughput serving engine for LLMs☆520Jan 8, 2026Updated 7 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆516Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆346Jul 2, 2024Updated 2 years ago
- Efficient LLM Inference over Long Sequences☆392Jun 25, 2025Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,622Jul 17, 2025Updated last year
- 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
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,512Feb 20, 2026Updated 6 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,478Aug 14, 2026Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆107Mar 26, 2025Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆186Jul 12, 2024Updated 2 years ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,169Apr 3, 2025Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,020Feb 5, 2026Updated 6 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆283Jul 6, 2025Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆8,027Updated this week