LLM Notes
  • Model Architecture
  • Infra
  • Search

Tags

  • Activation 1
  • Actor 1
  • Architecture 1
  • Attention 2
  • Batchnorm 1
  • Codebase 1
  • Decoding 1
  • Deepseek 1
  • Distributed-Training 1
  • Ffn 1
  • Flash-Attention 1
  • Glm 1
  • Gqa 1
  • Inference 1
  • Inference-System 1
  • Infra 2
  • Kv-Cache 2
  • Layernorm 1
  • Length-Extrapolation 1
  • Linear-Attention 1
  • Llm 1
  • Load-Balancing 1
  • Mamba 1
  • Megatron 2
  • Memory-Bound 1
  • Mha 1
  • Mid-Training 1
  • Minimax 1
  • Mixture-of-Experts 1
  • Mla 1
  • Model-Architecture 2
  • Moe 1
  • Mqa 1
  • Multi-Token-Prediction 1
  • Normalization 1
  • Ntk 1
  • Optimizer 1
  • Overview 1
  • Position-Encoding 1
  • Post-Training 3
  • Pre-Training 2
  • Prefill 1
  • Qwen 1
  • Ray 2
  • Rl 2
  • Rmsnorm 1
  • Roadmap 1
  • Rollout 1
  • Roofline 1
  • Rope 1
  • Routing 1
  • Sglang 1
  • Slime 2
  • Sparse-Attention 1
  • Sparse-Model 1
  • Speculative-Decoding 1
  • Swiglu 1
  • Training-Recipes 1
  • Training-Stability 1
  • Training-System 1
  • Transformer 3
  • Yarn 1
© 2026 LLM Notes · Powered by Hugo & PaperMod