liangyuwang / Tiny-DeepSpeedLinks
Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library
☆49Updated 4 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:
- Efficient Mixture of Experts for LLM Paper List☆154Updated 3 months ago
- qwen-nsa☆87Updated 3 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆283Updated 2 months ago
- ☆208Updated 2 months ago
- Tiny-Megatron, a minimalistic re-implementation of the Megatron library☆21Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆145Updated 3 weeks ago
- DeepSeek Native Sparse Attention pytorch implementation☆111Updated 3 weeks ago
- 青稞Talk☆184Updated last week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆98Updated 4 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆146Updated 9 months ago
- ☆150Updated 6 months ago
- Pipeline-Parallel Lecture: Simplest Dualpipe Implementation.☆31Updated 3 months ago
- ☆126Updated 7 months ago
- ☆66Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆198Updated last month
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆213Updated 4 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆183Updated last week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆330Updated 8 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆257Updated 5 months ago
- A set of examples based on verl for end-to-end RL training recipes.☆119Updated last week
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆184Updated 3 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆423Updated 3 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆191Updated 9 months ago
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆72Updated 9 months ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆279Updated 10 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆193Updated last month
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆222Updated 5 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆473Updated this week
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆52Updated 10 months ago
- (best/better) practices of megatron on veRL and tuning guide☆118Updated 3 months ago