microsoft / MInference
[NeurIPS'24 Spotlight, ICLR'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.
☆951Updated this week
Alternatives and similar repositories for MInference:
Users that are interested in MInference are comparing it to the libraries listed below
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,113Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆782Updated 6 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,221Updated 3 weeks ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,139Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆706Updated 6 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆620Updated last week
- Efficient LLM Inference over Long Sequences☆365Updated last month
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆789Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆617Updated 3 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆783Updated 6 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆442Updated last month
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆664Updated 2 weeks ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆348Updated 11 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆423Updated 2 months ago
- Ring attention implementation with flash attention☆717Updated last month
- FlashInfer: Kernel Library for LLM Serving☆2,532Updated this week
- A family of compressed models obtained via pruning and knowledge distillation☆330Updated 4 months ago
- Advanced Quantization Algorithm for LLMs/VLMs.☆413Updated this week
- Fast inference from large lauguage models via speculative decoding☆700Updated 7 months ago
- Scalable toolkit for efficient model alignment☆756Updated last week
- Fast, Flexible and Portable Structured Generation☆818Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆598Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,042Updated 10 months ago
- Muon is Scalable for LLM Training☆993Updated this week
- Minimalistic large language model 3D-parallelism training☆1,737Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆772Updated this week
- LongBench v2 and LongBench (ACL 2024)☆824Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆458Updated last week
- OLMoE: Open Mixture-of-Experts Language Models☆698Updated 2 weeks ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆661Updated this week