DL Notes

A focused knowledge base for modern deep learning systems, from hardware fundamentals to LLM serving and neural rendering.

Start Here

1. Hardware - GPU/NPU basics, memory systems, and practical GPU configuration
2. Tensor Operations - core tensor manipulations, activation functions, and CUDA Graph notes
3. AI Infra Metrics - TTFT, TPOT, and TPS
4. KV Cache - KV memory semantics, paged blocks, and prefix reuse
5. Serving Runtime - chunked prefill, admission control, and runtime-side stability
6. Parallelism - DP and TP from the perspective of memory, throughput, and communication
7. Decoding and Sampling - sampling policies and speculative decoding
8. Training Objective - autoregressive pre-training objective
9. Models - model-specific notes (Qwen3-Omni, DFlash) and practical serving commands
10. Neural Graphics - NeRF and Flow Matching foundations

Documentation Map

Systems and Infrastructure

• Hardware
• Tensor Operations

AI Infra

• Metrics
• KV Cache
• Serving Runtime
• Parallelism
• Decoding and Sampling
• Training Objective

Models

• Models

Graphics and Generative Modeling

• Neural Graphics

Scope

This site emphasizes practical understanding:

• concise theory with equations where useful
• implementation-minded notes and runnable snippets
• serving and performance considerations for real workloads