RiseAI-Sys / attention-gymLinks
Triton based sparse quantization attention kernel collection
☆38Updated 4 months ago
Alternatives and similar repositories for attention-gym
Users that are interested in attention-gym are comparing it to the libraries listed below
Sorting:
- High performance inference engine for diffusion models☆102Updated 4 months ago
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆73Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆204Updated last month
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆79Updated 5 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆144Updated 9 months ago
- ☆188Updated 11 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆48Updated last year
- A sparse attention kernel supporting mix sparse patterns☆423Updated 3 weeks ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆268Updated last month
- CUDA Templates for Linear Algebra Subroutines☆101Updated last year
- ☆84Updated 11 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆256Updated 5 months ago
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆45Updated 3 weeks ago
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆39Updated last year
- [ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitt…☆87Updated 9 months ago
- ☆125Updated 4 months ago
- ☆11Updated 11 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆93Updated 11 months ago
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆50Updated 2 years ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆153Updated 4 months ago
- Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”☆104Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆287Updated last year
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆72Updated 9 months ago
- Implement Flash Attention using Cute.☆100Updated last year
- ☆104Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆263Updated 6 months ago
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.☆22Updated last year
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆242Updated last month
- Examples of CUDA implementations by Cutlass CuTe☆264Updated 6 months ago
- ☆91Updated last month