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.
☆1,077Updated last month
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.☆1,419Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆846Updated 2 weeks ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆739Updated 9 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,260Updated 4 months ago
- Fast, Flexible and Portable Structured Generation☆1,078Updated last week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,664Updated last week
- OLMoE: Open Mixture-of-Experts Language Models☆814Updated 4 months ago
- Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLa…☆697Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆721Updated 4 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆477Updated 5 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆863Updated 10 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆647Updated 3 months ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆373Updated last year
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆828Updated 2 months ago
- Serving multiple LoRA finetuned LLM as one☆1,075Updated last year
- Efficient LLM Inference over Long Sequences☆385Updated last month
- Ring attention implementation with flash attention☆808Updated 3 weeks ago
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU. Seamlessly integrated with Torchao, Tra…☆531Updated this week
- Scalable toolkit for efficient model alignment☆829Updated 2 weeks ago
- Muon is Scalable for LLM Training☆1,211Updated 3 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆436Updated 6 months ago
- A high-performance inference system for large language models, designed for production environments.☆456Updated this week
- Fast inference from large lauguage models via speculative decoding☆782Updated 11 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆621Updated last year
- A family of compressed models obtained via pruning and knowledge distillation☆346Updated 8 months ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆733Updated 4 months ago
- An Open Source Toolkit For LLM Distillation☆683Updated 2 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,051Updated 2 weeks ago
- LLM KV cache compression made easy☆547Updated this week
- LongBench v2 and LongBench (ACL 25'&24')☆932Updated 6 months ago