TencentARC / mllm-npuLinks
mllm-npu: training multimodal large language models on Ascend NPUs
☆90Updated 9 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:
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆233Updated 2 weeks ago
- ☆167Updated 5 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆150Updated 7 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆64Updated 5 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆107Updated last week
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆48Updated 9 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆166Updated this week
- 🤗CacheDiT: A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers🔥☆61Updated this week
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆131Updated 2 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆355Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆209Updated last week
- A sparse attention kernel supporting mix sparse patterns☆238Updated 4 months ago
- Pruning the VLLMs☆96Updated 6 months ago
- Efficient Mixture of Experts for LLM Paper List☆72Updated 6 months ago
- Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆229Updated last month
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆105Updated 11 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆176Updated this week
- To pioneer training long-context multi-modal transformer models☆40Updated last week
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆204Updated 5 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆88Updated 5 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆133Updated last year
- [CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers☆51Updated 9 months ago
- MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer☆229Updated last year
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆275Updated 3 weeks ago
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆66Updated 9 months ago
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆44Updated 11 months ago
- ☆191Updated 2 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆104Updated 3 weeks ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆385Updated this week
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆102Updated 3 months ago