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.
☆776Updated this week
Related projects ⓘ
Alternatives and complementary repositories for MInference
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆815Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆661Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆629Updated last month
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆642Updated last month
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,000Updated 9 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,395Updated this week
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆476Updated this week
- OLMoE: Open Mixture-of-Experts Language Models☆435Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,143Updated 3 weeks ago
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆730Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆611Updated 2 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆433Updated 2 months ago
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆346Updated last week
- Serving multiple LoRA finetuned LLM as one☆979Updated 6 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆369Updated 3 weeks ago
- Fast inference from large lauguage models via speculative decoding☆562Updated 2 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆724Updated last month
- Scalable toolkit for efficient model alignment☆611Updated this week
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆236Updated 7 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆494Updated this week
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆299Updated 6 months ago
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆610Updated 5 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆553Updated 8 months ago
- Large Reasoning Models☆457Updated this week
- Minimalistic large language model 3D-parallelism training☆1,227Updated this week
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆435Updated 7 months ago
- ☆488Updated 3 weeks ago
- LLMPerf is a library for validating and benchmarking LLMs☆635Updated 2 months ago
- An Open Source Toolkit For LLM Distillation☆350Updated last month