| .. |
|
2026-09-05.md
|
c957beb710
eager A/B done (159 vs 158, rumor not confirmed); aiden 4x 163 = campaign record; night closed
|
hai 1 mes |
|
2026-09-07.md
|
7d850a136d
roce A/B: rocenante +31-90% decode on r27 4x dcp4 (160/176 vs 155), restore prod
|
hai 1 mes |
|
2026-09-08.md
|
f4abb53cbf
recipe [env] refs: values can resolve from recipe fields ({ from = "port" })
|
hai 1 mes |
|
2026-09-10.md
|
37e4be4a9f
r31 campaign: 4x A/B win (159/176, +10% decode), 2x below baseline, eugr recipe ready
|
hai 1 mes |
|
2026-09-11.md
|
7b9d588ac8
dsv41: b12x A/B — 167/176 (95, Excellent), +9 points and +18-33% speed
|
hai 1 mes |
|
2026-09-12.md
|
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)
|
hai 1 mes |
|
2026-09-13.md
|
2f717631ff
report: stale cross-check of run ledger vs live probe (orange + runlock hint); new 'sm121 runlock list|close' offline ledger command
|
hai 1 mes |
|
2026-09-18.md
|
498137d8b2
history: 09-18 end-state note (power off policy)
|
hai 1 mes |
|
2026-09-22.md
|
f1e87ec828
history: night 09-21/22 shift log (r39 verified, r38 4x repro, control baseline)
|
hai 1 mes |
|
2026-09-25.md
|
2aa9023c2f
bench: MiMo-V2.6-Pro-RL 8x first run — 165/176 (94/100), perf pp ~1.7K t/s
|
hai 4 semanas |
|
2026-09-26.md
|
548fcdfc75
dsv41 4x sglang aiden-1.6 (162/176) + qwen38 int4 1x (165/176) lanes, night shift 09-26
|
hai 3 semanas |
Alexander Korolev
548fcdfc75
dsv41 4x sglang aiden-1.6 (162/176) + qwen38 int4 1x (165/176) lanes, night shift 09-26