TencentARC / mllm-npuLinks
mllm-npu: training multimodal large language models on Ascend NPUs
☆91Updated 10 months ago
Alternatives and similar repositories for mllm-npu
Users that are interested in mllm-npu are comparing it to the libraries listed below
Sorting:
- Pruning the VLLMs☆97Updated 7 months ago
- ☆173Updated 5 months ago
- Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆238Updated 2 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆152Updated 8 months ago
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆49Updated 10 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆126Updated last week
- ☆171Updated 6 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆67Updated 5 months ago
- 🤗CacheDiT: A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers🔥☆99Updated this week
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆296Updated last week
- MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer☆230Updated last year
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆287Updated last month
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆40Updated last year
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆133Updated 3 months ago
- [EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner☆137Updated last month
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆28Updated this week
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆206Updated 6 months ago
- A Simple Framework of Small-scale LMMs for Video Understanding☆71Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆215Updated last month
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆179Updated 3 weeks ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆370Updated last week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆191Updated last week
- ☆115Updated 11 months ago
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆59Updated this week
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆244Updated 4 months ago
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆44Updated last year
- Efficient Mixture of Experts for LLM Paper List☆79Updated 7 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆105Updated last month
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆362Updated 2 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆323Updated 4 months ago