qingkelab / qingketalkLinks
青稞Talk
☆157Updated 2 weeks ago
Alternatives and similar repositories for qingketalk
Users that are interested in qingketalk are comparing it to the libraries listed below
Sorting:
- ☆205Updated last week
- Efficient Mixture of Experts for LLM Paper List☆142Updated last month
- qwen-nsa☆83Updated 3 weeks ago
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆180Updated 2 years ago
- ☆429Updated 2 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 2 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆193Updated last month
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆143Updated 7 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆170Updated 2 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆224Updated last week
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆48Updated 2 months ago
- DeepSeek Native Sparse Attention pytorch implementation☆107Updated last month
- FlagScale is a large model toolkit based on open-sourced projects.☆398Updated last week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆125Updated last week
- An industrial extension library of pytorch to accelerate large scale model training☆49Updated 2 months ago
- ☆148Updated 4 months ago
- Implementation of FlashAttention in PyTorch☆172Updated 9 months ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆411Updated 2 months ago
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆191Updated last week
- Speed Always Wins: A Survey on Efficient Architectures for Large Language Models☆353Updated 2 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆322Updated 6 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]☆192Updated 3 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆586Updated 3 weeks ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆138Updated last year
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆396Updated last month
- OpenSeek aims to unite the global open source community to drive collaborative innovation in algorithms, data and systems to develop next…☆237Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆244Updated 3 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆384Updated this week
- a-m-team's exploration in large language modeling☆191Updated 5 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆264Updated last month