qingkelab / qingketalkLinks
青稞Talk
☆146Updated this week
Alternatives and similar repositories for qingketalk
Users that are interested in qingketalk are comparing it to the libraries listed below
Sorting:
- ☆201Updated 5 months ago
- ☆425Updated last month
- Efficient Mixture of Experts for LLM Paper List☆129Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated last month
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆317Updated 5 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆214Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆192Updated 3 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆354Updated last week
- qwen-nsa☆74Updated 5 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆141Updated 5 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆426Updated this week
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆408Updated last month
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆45Updated last month
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆160Updated last month
- DeepSeek Native Sparse Attention pytorch implementation☆96Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆240Updated last month
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆242Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆570Updated last week
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆466Updated 2 weeks ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆1,122Updated this week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆255Updated 7 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆365Updated 3 weeks ago
- Speed Always Wins: A Survey on Efficient Architectures for Large Language Models☆331Updated 3 weeks ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆352Updated this week
- An industrial extension library of pytorch to accelerate large scale model training☆49Updated last month
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆177Updated 2 years ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆113Updated 5 months ago
- ☆143Updated 2 months ago
- An automated pipeline for evaluating LLMs for role-playing.☆200Updated last year
- mllm-npu: training multimodal large language models on Ascend NPUs☆92Updated last year