> Update 2026-09-05 (round 6, Prefill 11 + Prefill 12): on one NVIDIA > DGX Spark (GB10, sm121a) the round-6 binary measures > 644.78 / 641.94 tok/s cold prefill and 13.34 / 13.07 tok/s > decode on the campaign fixture (first 8,192 tokens of > promessisposi.txt plus 64 greedy tokens, context 8,257; campaign > baseline 286.55 / 5.52). Both rounds are scheduling only and > byte-identical to their kill switches and to the round-5 binary. > Prefill 11 > (8e886f1) > pipelines the K loop of the compact worklist MMQ kernel that runs > every routed expert projection (next block’s weights prefetched into > registers behind the MMA, activation halves staged with cp.async, > two barriers per iteration instead of four): +5.3% vs its kill > switch on the same binary. Prefill 12 > (12a2e14) > reads the HMMA prefill-attention fragments with ldmatrix and > prefetches the next K/V tile: +2.4%. Within one session the two > add up to 595.79 / 597.52 → 644.78 / 641.94 (+8.0%); the round-5 > numbers below were taken in an earlier session (prefill drifts a few > percent between sessions on one binary, so only same-binary pairs > are claimed). > > Round 5 (Prefill 9 + Prefill 10): the round-5 binary…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Baekpica
Теги: gguf, k2-horizon, mixed-quant, iq1_s, iq1_m, iq2_xxs, iq2_xs, imatrix
Лайков: 3 | Загрузок: 140
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
