microsoft / MoonlitLinks
This is a collection of our research on efficient AI, covering hardware-aware NAS and model compression.
☆86Updated 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☆123Updated 6 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆172Updated 2 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆68Updated last year
- LLM Inference with Microscaling Format☆34Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- Code Repository of Evaluating Quantized Large Language Models☆136Updated last year
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆38Updated last year
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆129Updated 2 years ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆67Updated 10 months ago
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆27Updated 9 months ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆67Updated 6 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆55Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆133Updated last year
- [AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models☆69Updated 2 years ago
- ☆157Updated 2 years ago
- ☆75Updated last month
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆84Updated last year
- ☆158Updated 11 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆65Updated last year
- ☆40Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆49Updated 3 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆207Updated 2 months ago
- ☆63Updated 2 years ago
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆49Updated last year
- AFPQ code implementation☆23Updated 2 years ago
- A framework to compare low-bit integer and float-point formats☆61Updated 3 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 10 months ago
- ☆77Updated last year