liangyuwang / Tiny-DeepSpeedLinks
Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library
☆48Updated 2 months ago
Alternatives and similar repositories for Tiny-DeepSpeed
Users that are interested in Tiny-DeepSpeed are comparing it to the libraries listed below
Sorting:
- qwen-nsa☆83Updated 3 weeks ago
- Efficient Mixture of Experts for LLM Paper List☆142Updated last month
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆264Updated last month
- ☆205Updated last week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆125Updated last week
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆170Updated 2 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 2 months ago
- ☆120Updated 5 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆143Updated 7 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆193Updated last month
- ☆148Updated 4 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆224Updated last week
- ☆65Updated 11 months ago
- 青稞Talk☆157Updated 2 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆244Updated 3 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆259Updated 5 months ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆220Updated 3 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆322Updated 6 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆138Updated last year
- DeepSeek Native Sparse Attention pytorch implementation☆107Updated last month
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 7 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆168Updated last month
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆384Updated this week
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆620Updated 2 weeks ago
- ☆211Updated 8 months ago
- Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this projec…☆28Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆49Updated 7 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆314Updated last month
- ☆83Updated 2 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆149Updated this week