microsoft / MInferenceLinks
[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.
☆1,035Updated this week
Alternatives and similar repositories for MInference
Users that are interested in MInference are comparing it to the libraries listed below
Sorting:
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,266Updated last week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆725Updated 8 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,249Updated 2 months ago
- A throughput-oriented high-performance serving framework for LLMs☆814Updated 3 weeks ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,417Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆637Updated last month
- Fast inference from large lauguage models via speculative decoding☆738Updated 9 months ago
- Fast, Flexible and Portable Structured Generation☆980Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆463Updated 3 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆686Updated 2 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆827Updated 8 months ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆705Updated 2 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆611Updated last year
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆357Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,060Updated last year
- Muon is Scalable for LLM Training☆1,049Updated 2 months ago
- Ring attention implementation with flash attention☆771Updated last week
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆962Updated 5 months ago
- LongBench v2 and LongBench (ACL 2024)☆883Updated 4 months ago
- Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLa…☆583Updated last week
- Large Context Attention☆711Updated 4 months ago
- FlashInfer: Kernel Library for LLM Serving☆3,044Updated this week
- Scalable toolkit for efficient model alignment☆803Updated last week
- Large Reasoning Models☆804Updated 5 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆506Updated this week
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆651Updated last year
- Minimalistic large language model 3D-parallelism training☆1,888Updated last week
- OLMoE: Open Mixture-of-Experts Language Models☆764Updated 2 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆808Updated last week
- An Open Source Toolkit For LLM Distillation☆612Updated 3 weeks ago