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.
☆944Updated 3 weeks ago
Alternatives and similar repositories for MInference:
Users that are interested in MInference are comparing it to the libraries listed below
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,103Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,057Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆773Updated 6 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆705Updated 5 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,216Updated 2 weeks ago
- Fast, Flexible and Portable Structured Generation☆812Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆771Updated 6 months ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆344Updated 11 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆617Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆611Updated 2 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆2,439Updated this week
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆659Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆597Updated last year
- Minimalistic large language model 3D-parallelism training☆1,701Updated this week
- A family of compressed models obtained via pruning and knowledge distillation☆329Updated 4 months ago
- Fast inference from large lauguage models via speculative decoding☆692Updated 7 months ago
- Efficient LLM Inference over Long Sequences☆365Updated last month
- Serving multiple LoRA finetuned LLM as one☆1,040Updated 10 months ago
- Scalable toolkit for efficient model alignment☆750Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆438Updated last month
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆393Updated 5 months ago
- LongBench v2 and LongBench (ACL 2024)☆815Updated 2 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆690Updated last week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆789Updated 5 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,313Updated this week
- Ring attention implementation with flash attention☆714Updated 3 weeks ago
- Advanced Quantization Algorithm for LLMs/VLMs.☆394Updated this week
- For releasing code related to compression methods for transformers, accompanying our publications☆416Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆452Updated this week
- Large Reasoning Models☆799Updated 3 months ago