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.
☆791Updated this week
Related projects ⓘ
Alternatives and complementary repositories for MInference
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆685Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆636Updated 2 months ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆826Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆647Updated last month
- For releasing code related to compression methods for transformers, accompanying our publications☆372Updated last month
- OLMoE: Open Mixture-of-Experts Language Models☆460Updated this week
- FlashInfer: Kernel Library for LLM Serving☆1,452Updated this week
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆491Updated 2 weeks ago
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,008Updated 10 months ago
- Serving multiple LoRA finetuned LLM as one☆984Updated 6 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆624Updated 2 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,149Updated last month
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆443Updated last week
- Official implementation of Half-Quadratic Quantization (HQQ)☆701Updated last week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆523Updated this week
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆373Updated 2 weeks ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆558Updated 8 months ago
- Minimalistic large language model 3D-parallelism training☆1,260Updated this week
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆737Updated last week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆731Updated last month
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆305Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆305Updated 3 months ago
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆613Updated 5 months ago
- LLMPerf is a library for validating and benchmarking LLMs☆645Updated 3 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆283Updated last week
- Advanced Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for t…☆248Updated this week
- Large Reasoning Models☆580Updated this week
- Scalable toolkit for efficient model alignment☆620Updated this week
- Fast inference from large lauguage models via speculative decoding☆569Updated 2 months ago
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆322Updated this week