Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.
☆675Jul 17, 2026Updated 3 months ago
Alternatives and similar repositories for Hy3
Users that are interested in Hy3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency☆479Apr 23, 2026Updated 6 months ago
- ☆405Aug 28, 2026Updated 2 months ago
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆1,038Updated this week
- MAGI-2-preview: Scaling Video Generation Models Efficiently☆641Aug 6, 2026Updated 2 months ago
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆11Updated this week
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence☆978Sep 17, 2026Updated last month
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,277Jul 9, 2026Updated 3 months ago
- ☆570Jul 8, 2026Updated 3 months ago
- Enhancing Representations through Heterogeneous Self-Supervised Learning (TPAMI 2025)☆15May 2, 2025Updated last year
- Open Frontier Intelligence☆9,034Aug 6, 2026Updated 2 months ago
- ☆1,630Nov 17, 2025Updated 11 months ago
- Official code for HiLS-Attention☆152Aug 13, 2026Updated 2 months ago
- Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.☆451Aug 27, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [arXiv 2026] This is the official PyTorch implementation of "MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators".☆99Aug 29, 2026Updated 2 months ago
- [ECCV2026] This is the official implementation of Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models☆43Jul 2, 2026Updated 4 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,295Oct 26, 2026Updated last week
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆3,297Jun 23, 2026Updated 4 months ago
- A curated list of models, benchmarks, tools and guides for audio editing☆52Updated this week
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- dots3 note preview☆147Aug 14, 2026Updated 2 months ago
- Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory☆182Sep 7, 2026Updated last month
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- RationalRewards: a reasoning reward model for diffusion RL and test-time prompt tuning☆61Jun 4, 2026Updated 4 months ago
- ☆146Feb 17, 2026Updated 8 months ago
- [ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis☆792May 23, 2026Updated 5 months ago
- [ECCV 2024] Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation☆40Mar 3, 2025Updated last year
- 把 On-Policy Distillation 接到 DSpark。☆19Jun 28, 2026Updated 4 months ago
- DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers☆527Sep 30, 2026Updated last month
- Official Code for 'TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction' (ICCV 2025)☆79Nov 8, 2025Updated 11 months ago
- A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.☆283Sep 30, 2026Updated last month
- Hunyuan 3D Part Segmentation and Generation Pipeline☆556Dec 5, 2025Updated 10 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Accepted to MLSys 2026☆97Apr 19, 2026Updated 6 months ago
- flex-block-attn: an efficient block sparse attention computation library☆133Dec 26, 2025Updated 10 months ago
- ☆20May 28, 2025Updated last year
- Agent skill and toolkit for reconstructing Gaussian splats as editable Blender Geometry Nodes meshes and Shader Node materials.☆73Oct 24, 2026Updated last week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆967Updated this week
- A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).☆1,210Updated this week
- [🚀 ICLR 2026 Oral] NextStep-1: SOTA Autogressive Image Generation with Continuous Tokens. A research project developed by the StepFun’s …☆696Feb 27, 2026Updated 8 months ago