microsoft / MInference
[NeurIPS'24 Spotlight] 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.
☆874Updated 2 weeks ago
Alternatives and similar repositories for MInference:
Users that are interested in MInference are comparing it to the libraries listed below
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆851Updated this week
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆912Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆692Updated 3 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,179Updated 3 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆687Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,797Updated this week
- OLMoE: Open Mixture-of-Experts Language Models☆531Updated last month
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆561Updated this week
- Efficient, Flexible and Portable Structured Generation☆570Updated this week
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,083Updated last year
- veRL: Volcano Engine Reinforcement Learning for LLM☆690Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,012Updated 8 months ago
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆417Updated 2 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆680Updated 4 months ago
- Minimalistic large language model 3D-parallelism training☆1,386Updated this week
- A family of compressed models obtained via pruning and knowledge distillation☆309Updated 2 months ago
- Efficient LLM Inference over Long Sequences☆344Updated 2 weeks ago
- For releasing code related to compression methods for transformers, accompanying our publications☆399Updated 3 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆754Updated 3 months ago
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆565Updated last week
- Official implementation of Half-Quadratic Quantization (HQQ)☆732Updated this week
- Advanced Quantization Algorithm for LLMs/VLMs.☆344Updated this week
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆634Updated 7 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆578Updated 10 months ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆320Updated 8 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆481Updated 2 months ago
- An Open Source Toolkit For LLM Distillation☆425Updated last week
- Scalable toolkit for efficient model alignment☆674Updated this week
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆377Updated 3 months ago
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆447Updated 9 months ago