Alexander Korolev d5a2032562 bench: warm-prefix depth measurement (--benchy-args=--enable-prefix-caching) — the c2 long-context 'collapse' (13.7/5.6/2.1) was llama-benchy's default cold-monolith branch, proven artifact (flag flips c2@65K 13.7 -> 52.1, TTFT 28.3s -> 1.5s); drop DEBUG from sparkring recipe (diagnosis closed) 3 недель назад
..
reports 6044b3d669 sparkring lane: A/B max-model-len 524288 -> their qualified 262144 (c2 collapse axis; kv pin still off, pool auto per operator) 3 недель назад
recipe.toml d5a2032562 bench: warm-prefix depth measurement (--benchy-args=--enable-prefix-caching) — the c2 long-context 'collapse' (13.7/5.6/2.1) was llama-benchy's default cold-monolith branch, proven artifact (flag flips c2@65K 13.7 -> 52.1, TTFT 28.3s -> 1.5s); drop DEBUG from sparkring recipe (diagnosis closed) 3 недель назад