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.
☆971Updated last 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.☆1,183Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆797Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆803Updated 7 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆715Updated 6 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,251Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆643Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,242Updated last month
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆352Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆598Updated last year
- Fast inference from large lauguage models via speculative decoding☆714Updated 8 months ago
- Advanced Quantization Algorithm for LLMs/VLMs.☆438Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆791Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆453Updated 2 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆716Updated last month
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆681Updated last month
- Minimalistic large language model 3D-parallelism training☆1,793Updated this week
- FlashInfer: Kernel Library for LLM Serving☆2,693Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆628Updated 3 weeks ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆800Updated 6 months ago
- LongBench v2 and LongBench (ACL 2024)☆845Updated 3 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆424Updated 3 months ago
- Ring attention implementation with flash attention☆743Updated 2 weeks ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆444Updated 7 months ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆696Updated last week
- LLM KV cache compression made easy☆458Updated last week
- Efficient LLM Inference over Long Sequences☆368Updated last week
- A family of compressed models obtained via pruning and knowledge distillation☆334Updated 5 months ago
- Fast, Flexible and Portable Structured Generation☆888Updated 2 weeks ago
- Serving multiple LoRA finetuned LLM as one☆1,054Updated 11 months ago
- Muon is Scalable for LLM Training☆1,029Updated 3 weeks ago