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.
☆1,059Updated last 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.☆1,345Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆834Updated last month
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆734Updated 9 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,259Updated 3 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆711Updated 3 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆618Updated last year
- Ring attention implementation with flash attention☆793Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆848Updated 10 months ago
- Fast inference from large lauguage models via speculative decoding☆766Updated 10 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆470Updated 4 months ago
- Efficient LLM Inference over Long Sequences☆379Updated last week
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆367Updated last year
- OLMoE: Open Mixture-of-Experts Language Models☆792Updated 3 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,587Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆647Updated 2 months ago
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…