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.
☆1,098Updated 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.☆1,462Updated last week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆739Updated 10 months ago
- A throughput-oriented high-performance serving framework for LLMs☆868Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,270Updated 5 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆836Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆732Updated 5 months ago
- Fast, Flexible and Portable Structured Generation☆1,153Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆875Updated 11 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆438Updated 6 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,783Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆651Updated 3 months ago
- Serving multiple LoRA finetuned LLM as one☆1,082Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆488Updated 6 months ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆375Updated last year
- Fast inference from large lauguage models via speculative decoding☆799Updated 11 months ago
- slime is a LLM post-training framework aiming for RL Scaling.☆1,302Updated this week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆838Updated 2 months ago
- LongBench v2 and LongBench (ACL 25'&24')☆944Updated 7 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆629Updated last year
- Ring attention implementation with flash attention☆836Updated last week
- Scalable toolkit for efficient model alignment☆835Updated 2 weeks ago
- A family of compressed models obtained via pruning and knowledge distillation☆347Updated 9 months ago
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU. Seamlessly integrated with Torchao, Tra…☆588Updated this week
- Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLa…☆727Updated last week
- An Open Source Toolkit For LLM Distillation☆707Updated last month
- Muon is Scalable for LLM Training☆1,258Updated last week
- Large Reasoning Models☆805Updated 8 months ago
- Efficient LLM Inference over Long Sequences☆387Updated last month
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆980Updated 8 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆859Updated this week