mit-han-lab / deepcompressor
Model Compression Toolbox for Large Language Models and Diffusion Models
☆435Updated 3 weeks ago
Alternatives and similar repositories for deepcompressor:
Users that are interested in deepcompressor are comparing it to the libraries listed below
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆243Updated 3 weeks ago
- 📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉☆210Updated last month
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆453Updated last week
- ☆160Updated 3 months ago
- [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.☆348Updated last year
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆677Updated 4 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆77Updated last month
- ☆170Updated this week
- A parallelism VAE avoids OOM for high resolution image generation☆61Updated 3 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆376Updated 4 months ago
- The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models☆99Updated last year
- A sparse attention kernel supporting mix sparse patterns☆192Updated 2 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆342Updated 2 months ago
- 📚 Collection of awesome generation acceleration resources.☆215Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆248Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆477Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆643Updated last month
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆248Updated 5 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆125Updated 2 months ago
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆132Updated last month
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆196Updated 2 months ago
- EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆263Updated 6 months ago
- This repository contains integer operators on GPUs for PyTorch.☆202Updated last year
- Quantized Attention achieves speedup of 2-3x and 3-5x compared to FlashAttention and xformers, without lossing end-to-end metrics across …☆1,380Updated this week
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆127Updated 2 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆35Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆184Updated this week
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆140Updated 3 weeks ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆886Updated 9 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆86Updated 3 months ago