RoPE

Pick the recipe a 2026 frontier open-weight LLM block actually ships

Order the three steps of a position-interpolation fine-tune that takes RoPE from 4k to 16k.

Llama-3 bumps RoPE base from 10k to 500k, which long-context property follows?

RoPE, spell out the acronym and name exactly which vectors it rotates

Contrast absolute and relative positional encoding by what the score depends on

Match GPT-2 versus Llama-2 attention design choices to their differences

Contrast ALiBi's linear distance bias with RoPE's vector rotation, which one modifies scores additively, and which one modifies Q and K directly?

Extending a 4k-context model to 32k via FT: how RoPE scaling fits in

Why does pure long-context FT (without RoPE scaling) fail to extrapolate?

How are RoPE NTK scaling and YaRN used at inference time to extend context beyond the training length?

Why has RoPE become the dominant positional encoding in modern LLMs?

How does RoPE differ structurally from sinusoidal positional encoding?

How do you extend a pretrained LLM's context window beyond its training length using position interpolation / YaRN?