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.
☆1,124Updated last month
Alternatives and similar repositories for MInference
Users that are interested in MInference are comparing it to the libraries listed below
Sorting:
- A throughput-oriented high-performance serving framework for LLMs☆887Updated last month
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆745Updated 11 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,635Updated last week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,277Updated 6 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆753Updated 6 months ago
- Fast, Flexible and Portable Structured Generation☆1,233Updated this week
- OLMoE: Open Mixture-of-Experts Language Models☆863Updated 6 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆895Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆490Updated 7 months ago
- Ring attention implementation with flash attention☆866Updated last week
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆778Updated this week
- Fast inference from large lauguage models via speculative decoding☆815Updated last year
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆382Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,086Updated last year
- Efficient LLM Inference over Long Sequences☆391Updated 2 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,950Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆655Updated 4 months ago
- LongBench v2 and LongBench (ACL 25'&24')☆963Updated 8 months ago
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆987Updated 9 months ago
- Scalable toolkit for efficient model alignment☆838Updated last month
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.☆631Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆630Updated last year
- A high-performance inference system for large language models, designed for production environments.☆465Updated this week
- slime is a LLM post-training framework for RL Scaling.☆1,747Updated this week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆847Updated 3 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆351Updated 10 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆438Updated 11 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆444Updated 8 months ago
- LLM KV cache compression made easy☆609Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆878Updated last week