[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.
☆1,188Sep 30, 2025Updated 4 months ago
Alternatives and similar repositories for MInference
Users that are interested in MInference are comparing it to the libraries listed below
Sorting:
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆372Jul 10, 2025Updated 7 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆358Nov 20, 2025Updated 3 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆525Feb 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…☆816Mar 6, 2025Updated 11 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,009Updated this week
- ☆303Jul 10, 2025Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,018Sep 4, 2024Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆504Aug 1, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆946Oct 29, 2025Updated 3 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,795Updated this week
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆283May 1, 2025Updated 9 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Oct 13, 2025Updated 4 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆404Aug 13, 2024Updated last year
- A sparse attention kernel supporting mix sparse patterns☆459Jan 18, 2026Updated last month
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆659Sep 30, 2025Updated 4 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,188Feb 20, 2026Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆277Aug 31, 2024Updated last year
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆446Oct 16, 2024Updated last year
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,658Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,901Feb 20, 2026Updated last week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,315Mar 6, 2025Updated 11 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,708Jun 25, 2024Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,441Jul 17, 2025Updated 7 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆250Dec 16, 2024Updated last year
- Ring attention implementation with flash attention☆986Sep 10, 2025Updated 5 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆463May 30, 2025Updated 8 months ago
- LLM KV cache compression made easy☆925Feb 18, 2026Updated last week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,428Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,002Jan 18, 2026Updated last month
- A low-latency & high-throughput serving engine for LLMs☆476Jan 8, 2026Updated last month
- ☆65Apr 26, 2025Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆336Jul 2, 2024Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,618Updated this week
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆396Apr 20, 2024Updated last year
- Efficient LLM Inference over Long Sequences☆392Jun 25, 2025Updated 8 months ago
- Efficient Triton Kernels for LLM Training☆6,148Feb 20, 2026Updated last week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,054Apr 3, 2025Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆177Jul 12, 2024Updated last year