[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.
☆1,220Apr 8, 2026Updated 2 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☆397Jul 10, 2025Updated 11 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆411Nov 20, 2025Updated 7 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…☆844Mar 6, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,867Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆321Jul 10, 2025Updated 11 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆169Oct 13, 2025Updated 8 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆523Aug 1, 2024Updated last year
- A sparse attention kernel supporting mix sparse patterns☆528Jan 18, 2026Updated 5 months ago
- A throughput-oriented high-performance serving framework for LLMs☆962Mar 29, 2026Updated 2 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆720Apr 15, 2026Updated 2 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆308May 1, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,095Sep 4, 2024Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆254Dec 16, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [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☆429Aug 13, 2024Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,672Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆151Dec 4, 2024Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,418Feb 20, 2026Updated 4 months ago
- [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☆2,749Jun 25, 2024Updated 2 years ago
- ☆65Apr 26, 2025Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,337Mar 6, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆29,694Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,141Updated this week
- LLM KV cache compression made easy☆1,120Updated this week
- Ring attention implementation with flash attention☆1,026Sep 10, 2025Updated 9 months ago
- A low-latency & high-throughput serving engine for LLMs☆507Jan 8, 2026Updated 5 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,249Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆498Jun 10, 2026Updated 2 weeks ago
- Efficient LLM Inference over Long Sequences☆394Jun 25, 2025Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆342Jul 2, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,578Jul 17, 2025Updated 11 months ago
- 16-fold memory access reduction with nearly no loss☆107Mar 26, 2025Updated last year
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,355Updated this week
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆405Apr 20, 2024Updated 2 years ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆183Jul 12, 2024Updated last year
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,129Apr 3, 2025Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,006Feb 5, 2026Updated 4 months ago