xlite-dev / Awesome-Diffusion-Inference
πA curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. ππ
β201Updated last week
Alternatives and similar repositories for Awesome-Diffusion-Inference:
Users that are interested in Awesome-Diffusion-Inference are comparing it to the libraries listed below
- Model Compression Toolbox for Large Language Models and Diffusion Modelsβ394Updated last month
- β155Updated 2 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationβ69Updated last week
- Context parallel attention that accelerates DiT model inference with dynamic cachingβ228Updated last week
- A parallelism VAE avoids OOM for high resolution image generationβ57Updated 2 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.β385Updated 2 weeks ago
- flash attention tutorial written in python, triton, cuda, cutlassβ308Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ458Updated last week
- Puzzles for learning Triton, play it with minimal environment configuration!β267Updated 3 months ago
- β140Updated this week
- π Collection of awesome generation acceleration resources.β182Updated this week
- A sparse attention kernel supporting mix sparse patternsβ169Updated last month
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelsβ670Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ260Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Trainingβ168Updated last month
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papβ¦β238Updated 3 weeks ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clustersβ44Updated 8 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttentionβ326Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Seβ¦β617Updated 3 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.β253Updated 9 months ago
- Efficient LLM Inference over Long Sequencesβ365Updated last month
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline modβ¦β423Updated 6 months ago
- πFFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) GPU SRAM complexity for headdim > 256, ~2xβπvs SDPA EA.β157Updated this week
- [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.β347Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.β109Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Servingβ301Updated 8 months ago
- Accelerating Diffusion Transformers with Token-wise Feature Cachingβ115Updated 2 weeks ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.β433Updated 7 months ago
- The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Modelsβ96Updated last year
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional varβ¦β121Updated last month