Junhui's Journal 2
  • Home
  • Tags
  • Categories

Tags

  • Actor-Critic 3
  • Agent 24
  • Attention 1
  • Bank 3
  • BPE 1
  • CICD 3
  • clash 1
  • Compiler 4
  • Cooperative Groups 1
  • CTA 1
  • cuBLAS 1
  • CUDA 38
  • cuda-gdb 1
  • datasets library 1
  • DQN 1
  • Event 1
  • Fine Tune 1
  • General 4
  • GGML 1
  • GGUF 1
  • git 1
  • github actions 1
  • Grouped Query Attention 1
  • GRPO 5
  • Intrinsics 1
  • jenkins 1
  • Jetson 4
  • KL Divergence 2
  • kv-cache 1
  • LangChain 3
  • LangGraph 6
  • linux 1
  • llama.cpp 8
  • LlamaHub 1
  • LlamaIndex 4
  • LLM 23
  • LoRA 1
  • MARL 1
  • MCP 1
  • Multi-agent System 2
  • Nsight Compute 2
  • Nsight Systems 1
  • nvcc 1
  • Ollama 2
  • Optuna 1
  • Pinned Memory 1
  • Policy-Based Methods 1
  • PPO 2
  • prompts.yaml 2
  • proxy 1
  • python 1
  • Q-learning 1
  • RAG 3
  • ReAct 1
  • Reinforcement Learning 13
  • RLHF 1
  • Sampling 1
  • Shared Memory 3
  • shell 1
  • SIMD 2
  • SIMT 1
  • SM 2
  • Smolagents 7
  • SMSP 1
  • Stream 1
  • TAO 1
  • Tensor Core 3
  • Tokenizer 2
  • Tonkenizer 3
  • Transformer 2
  • Triton 2
  • TRL 2
  • Unified Memory 1
  • Unsloth 1
  • Value-Based Methods 1
  • Vectorization 2
  • VLM 1
  • Warp 2
© 2025 Junhui's Journal 2 ยท Powered by Hugo & PaperMod