 Alexander Korolev
|
2bde637398
r36 @512K + Engram NVMe: 154/176, 3,774 pp / 822 ms TTFT (2.3x prod prefill, decode -3%) — candidate lane; + forum 381350#521 b12x loader finding (verified: 320B/18B from the checkpoint config)
|
1 месяц назад |
|
Alexander Korolev
|
f042556790
r36 dev65 + local Engram: prefill 3,654 pp / 826 ms TTFT (9.1x the NFS run, 2.2x prod) — storage suspect confirmed; 149/176 = variance + K7 stack gap; lane is now a candidate
|
1 месяц назад |
|
Alexander Korolev
|
a02c574b51
dsv41 lab r36 A/B: builds + works on GB10 (DSpark K7, Engram disk/io_uring, 3.38M KV) but loses — 158/176 vs 167 prod, prefill 401 vs 1,642 pp (suspect: io_uring over NFS); eugr stays prod
|
1 месяц назад |
|
Alexander Korolev
|
743b5a7706
dflash2 night A/B: 4x 165/176 (+2, prefill +27%, TTFT -31%) vs MTP3; 2x Spark blocked (C4 page-stride + interleave%4 gates); history + spec
|
1 месяц назад |
|
Alexander Korolev
|
d6bba73685
r35 promoted to GLM 4x production (operator decision); r31 stays as rollback lane
|
1 месяц назад |
|
Alexander Korolev
|
e8ac5f1bd7
r35 A/B: 163/176 (dev65) vs r31 159 (dev46), perf flat, TC-33/80 fixed, TC-51 new; report + state
|
1 месяц назад |
|
Alexander Korolev
|
a902dd0124
night 09-12: eugr 166/176, sparkring 8b32ef2 reliability FAIL (again), Aiden 1.1 DCP2 A/B 158/176 (b12x lane wins); r31 back to prod, dgx5 off
|
1 месяц назад |
