MoonshotAI / MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
☆1,768Updated last month
Alternatives and similar repositories for MoBA:
Users that are interested in MoBA are comparing it to the libraries listed below
- Muon is Scalable for LLM Training☆1,039Updated last month
- Official Repo for Open-Reasoner-Zero☆1,904Updated last month
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆1,698Updated this week
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,198Updated 3 weeks ago
- ☆739Updated 2 weeks ago
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆2,127Updated last week
- Democratizing Reinforcement Learning for LLMs☆3,182Updated 3 weeks ago
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆2,586Updated 3 weeks ago
- Simple RL training for reasoning☆3,519Updated 3 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,529Updated last month
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆2,258Updated this week
- An Open Large Reasoning Model for Real-World Solutions☆1,488Updated 2 months ago
- Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities☆819Updated 2 weeks ago
- Fully open data curation for reasoning models☆1,742Updated last month
- Distributed RL System for LLM Reasoning☆1,205Updated last week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆647Updated last month
- verl: Volcano Engine Reinforcement Learning for LLMs☆7,626Updated this week
- Large Reasoning Models☆804Updated 5 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,751Updated last month
- Expert Parallelism Load Balancer☆1,161Updated last month
- Analyze computation-communication overlap in V3/R1.☆1,012Updated last month
- ☆679Updated 3 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,184Updated this week
- A fork to add multimodal model training to open-r1☆1,245Updated 3 months ago
- O1 Replication Journey☆1,986Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆2,788Updated this week
- Witness the aha moment of VLM with less than $3.☆3,622Updated 2 months ago
- Reproduce R1 Zero on Logic Puzzle☆2,327Updated last month
- Training Large Language Model to Reason in a Continuous Latent Space☆1,094Updated 3 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,005Updated this week