qingkelab / qingketalkLinks
青稞Talk
☆139Updated this week
Alternatives and similar repositories for qingketalk
Users that are interested in qingketalk are comparing it to the libraries listed below
Sorting:
- Efficient Mixture of Experts for LLM Paper List☆123Updated this week
- qwen-nsa☆74Updated 4 months ago
- ☆198Updated 4 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆67Updated last week
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆179Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆189Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆349Updated this week
- ☆413Updated 3 weeks ago
- TransMLA: Multi-Head Latent Attention Is All You Need☆349Updated this week
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆177Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆236Updated 3 weeks ago
- DeepSeek Native Sparse Attention pytorch implementation☆92Updated last month
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆310Updated 4 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆402Updated last week
- ☆143Updated 2 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆139Updated 4 months ago
- An industrial extension library of pytorch to accelerate large scale model training☆47Updated 3 weeks ago
- ☆46Updated 3 months ago
- ☆146Updated 6 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆110Updated 4 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆556Updated last month
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆43Updated 2 weeks ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆406Updated 2 weeks ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆248Updated 6 months ago
- ☆79Updated last year
- Implementation of FlashAttention in PyTorch☆164Updated 7 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆321Updated this week
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆145Updated last week
- mllm-npu: training multimodal large language models on Ascend NPUs☆91Updated last year