microsoft / MoonlitLinks
This is a collection of our research on efficient AI, covering hardware-aware NAS and model compression.
☆84Updated last year
Alternatives and similar repositories for Moonlit
Users that are interested in Moonlit are comparing it to the libraries listed below
Sorting:
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆121Updated 4 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆126Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆67Updated 7 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆162Updated last week
- ☆156Updated 2 years ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆66Updated last year
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆129Updated 2 years ago
- ☆58Updated last year
- [AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models☆62Updated last year
- LLM Inference with Microscaling Format☆32Updated 11 months ago
- Code Repository of Evaluating Quantized Large Language Models☆135Updated last year
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆57Updated 4 months ago
- 16-fold memory access reduction with nearly no loss☆106Updated 7 months ago
- ☆69Updated 3 months ago
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆45Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆47Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆326Updated last year
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆28Updated 8 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆148Updated 3 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆53Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆61Updated last year
- ☆61Updated 2 years ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆245Updated 4 months ago
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆48Updated 3 years ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆144Updated 8 months ago
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆94Updated 11 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆151Updated 3 weeks ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆110Updated last year
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆38Updated last year