nvidia-cosmos / cosmos-xennaLinks
Python library for building and running distributed data pipelines using Ray
☆33Updated last week
Alternatives and similar repositories for cosmos-xenna
Users that are interested in cosmos-xenna are comparing it to the libraries listed below
Sorting:
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆73Updated last week
- CATransformers is a framework for joint neural network and hardware architecture search.☆17Updated 4 months ago
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated last year
- Experimental scripts for researching data adaptive learning rate scheduling.☆22Updated last year
- Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.☆150Updated last week
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆45Updated 2 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆28Updated this week
- API serving for your diffusers models☆11Updated last year
- NASRec Weight Sharing Neural Architecture Search for Recommender Systems☆30Updated last year
- ☆33Updated 3 months ago
- imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video…☆36Updated last year
- ☆46Updated last year
- DTensor-native pretraining and fine-tuning for LLMs/VLMs with day-0 Hugging Face support, GPU-acceleration, and memory efficiency.☆81Updated this week
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning☆191Updated last month
- [WIP] Better (FP8) attention for Hopper☆32Updated 7 months ago
- ☆85Updated last year
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆52Updated 6 months ago
- Implementation of a methodology that allows all sorts of user defined GPU kernel fusion, for non CUDA programmers.☆25Updated this week
- ☆39Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Updated 11 months ago
- Simple large-scale training of stable diffusion with multi-node support.☆134Updated 2 years ago
- Description and applications of OpenAI's paper about DALL-E (2021) and implementation of other (CLIP-guided) zero-shot text-to-image gene…☆33Updated 3 years ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆38Updated 2 weeks ago
- vLLM adapter for a TGIS-compatible gRPC server.☆40Updated this week
- Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.☆123Updated 3 months ago
- Train, tune, and infer Bamba model☆132Updated 3 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆103Updated 10 months ago
- DPO, but faster 🚀☆44Updated 9 months ago
- Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)☆30Updated last year
- A block oriented training approach for inference time optimization.☆34Updated last year