The official source reports this update: b10707: kv-cells: stop the sequence scan once all sequences are seen. kv-cells: stop the sequence scan once all sequences are seen ( #28011 ) for_each_token_in tested all LLAMA_MAX_SEQ sequences for every used cell, while a cell almost always belongs to one. The scan now stops once the cell's own sequences have been seen. Same visit order, same callback arguments, so behaviour is unchanged. get_prev_tokens is the only caller, so this affects the n-gram path.
Canonical AI event
Llama.cpp optimizes sequence scan for faster context generation.
The sequence scan in kv-cells now stops after seeing all relevant sequences, improving speed by up to 39% on large contexts.
31 Aug 20261 verified claims1 sources1 observations
This official update documents a development concerning b10707: kv-cells: stop the sequence scan once all sequences are seen. Its practical significance depends on the scope and evidence stated by the source.
Read the official source update and verify its stated scope, evidence and timing before acting on it.
Connected knowledge
Entities affected by this event
Evidence trail
Sources behind the event
Editorial presentation
Open story