Alternatives and similar repositories for mllm-npu

Users that are interested in mllm-npu are comparing it to the libraries listed below

• AdaCache-DiT / AdaCache
  Adaptive Caching for Faster Video Generation with Diffusion Transformers
  ☆147Updated 7 months ago
• thu-nics / DiTFastAttn
  ☆167Updated 4 months ago
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆64Updated 4 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆203Updated 2 weeks ago
• maomaocun / dLLM-cache
  Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…
  ☆72Updated this week
• mit-han-lab / x-attention
  XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆158Updated 3 weeks ago
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆166Updated last week
• Visual-Agent / DeepEyes
  ☆269Updated last week
• ByteDance-Seed / VeOmni
  VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework
  ☆339Updated 3 weeks ago
• GAIR-NLP / MAYE
  Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
  ☆127Updated last month
• Victorwz / Open-Qwen2VL
  Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
  ☆216Updated 2 weeks ago
• Vchitect / LiteGen
  A light-weight and high-efficient training framework for accelerating diffusion tasks.
  ☆47Updated 8 months ago
• OpenGVLab / MM-Interleaved
  MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer
  ☆225Updated last year
• NVlabs / Fast-dLLM
  ☆78Updated last week
• ZhangAIPI / YOPO_MLLM_Pruning
  Pruning the VLLMs
  ☆95Updated 5 months ago
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆132Updated 11 months ago
• RUCAIBox / Virgo
  Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*
  ☆103Updated last week
• mit-han-lab / vila-u
  [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  ☆330Updated last month
• horseee / learning-to-cache
  [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  ☆103Updated 10 months ago
• SparksJoe / Prism
  A Framework for Decoupling and Assessing the Capabilities of VLMs
  ☆43Updated 11 months ago
• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆219Updated 3 months ago
• SandAI-org / MagiAttention
  A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
  ☆372Updated last week
• KangarooGroup / Kangaroo
  official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
  ☆65Updated 9 months ago
• Juanerx / Q-DiT
  [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
  ☆50Updated 9 months ago
• FreedomIntelligence / LongLLaVA
  LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
  ☆203Updated 4 months ago
• alibaba / conv-llava
  ☆115Updated 10 months ago
• prathebaselva / FORA
  FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.
  ☆46Updated 10 months ago
• yfzhang114 / r1_reward
  ✨✨R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
  ☆136Updated 3 weeks ago
• Tele-AI / TeleTron
  To pioneer training long-context multi-modal transformer models
  ☆38Updated this week
• thu-nics / ViDiT-Q
  [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  ☆98Updated 2 months ago