#llm - Tags - ML Learning Lab

8 posts · Transformer Series

Tag: #llm

🗓 2026-04-11 • Transformer Series • ⏱ 62 min read

Large model quantization fundamentals: outliers, superweights, massive activations, PTQ, QAT, and common quantization strategies.

🗓 2026-04-11 • Transformer Series • ⏱ 32 min read

Medusa: multi-decoding heads, tree attention, typical acceptance, sparse tree construction, training strategies, and decoding flow.

🗓 2026-04-09 • Transformer Series • ⏱ 49 min read

Length extrapolation in Transformers and LLMs: position encoding methods, RoPE extrapolation, PI, NTK-aware interpolation, YaRN, and Giraffe.

🗓 2026-04-05 • Transformer Series • ⏱ 47 min read

RoPE positional encoding, derivation, properties, extrapolation, and implementation.

🗓 2026-03-31 • Transformer Series • ⏱ 76 min read

Transformer overall architecture: workflow, attention modules, construction from Harvard code, and theoretical perspectives.

🗓 2026-03-27 • [OpenHands] AI Agent Frameworks • ⏱ 19 min read

OpenHands Agent internals: state management, agent types, state lifecycle, and LLM adapter design.

🗓 2026-03-27 • [OpenHands] AI Agent Frameworks • ⏱ 17 min read

OpenHands CodeActAgent internals: design principles, tools, context engineering, and workflow.

🗓 2026-03-27 • [OpenHands] AI Agent Frameworks • ⏱ 22 min read

OpenHands function-calling internals: tool design, action mapping, and robust parsing of LLM tool calls.