| .. |
|
2026-09-08_190654_r28-4x-dcp4.json
|
15e9b62ca7
build: named version profiles (build_profile) + full r28 pin set (b12x 7216f6b9, lmcache 934c287a)
|
1 mēnesi atpakaļ |
|
2026-09-08_190654_r28-4x-dcp4.log
|
15e9b62ca7
build: named version profiles (build_profile) + full r28 pin set (b12x 7216f6b9, lmcache 934c287a)
|
1 mēnesi atpakaļ |
|
2026-09-08_190654_r28-4x-dcp4.md
|
15e9b62ca7
build: named version profiles (build_profile) + full r28 pin set (b12x 7216f6b9, lmcache 934c287a)
|
1 mēnesi atpakaļ |
|
2026-09-08_204414_r28-4x-dcp4-full.json
|
01a63d9cc5
bench: full r28 4x DCP4 — 155/176 (vs r27 160, mixed 159); 8 hard-scenario flips under full-stack noise band
|
1 mēnesi atpakaļ |
|
2026-09-08_204414_r28-4x-dcp4-full.log
|
01a63d9cc5
bench: full r28 4x DCP4 — 155/176 (vs r27 160, mixed 159); 8 hard-scenario flips under full-stack noise band
|
1 mēnesi atpakaļ |
|
2026-09-08_204414_r28-4x-dcp4-full.md
|
01a63d9cc5
bench: full r28 4x DCP4 — 155/176 (vs r27 160, mixed 159); 8 hard-scenario flips under full-stack noise band
|
1 mēnesi atpakaļ |
|
2026-09-08_211618_r28-4x-dcp4-full-rerun.json
|
d1f10dd1e7
bench: r28 full rerun 159/176 — 155 vs 160 was run-to-run variance (8 flips), not a regression
|
1 mēnesi atpakaļ |
|
2026-09-08_211618_r28-4x-dcp4-full-rerun.log
|
d1f10dd1e7
bench: r28 full rerun 159/176 — 155 vs 160 was run-to-run variance (8 flips), not a regression
|
1 mēnesi atpakaļ |
|
2026-09-08_211618_r28-4x-dcp4-full-rerun.md
|
d1f10dd1e7
bench: r28 full rerun 159/176 — 155 vs 160 was run-to-run variance (8 flips), not a regression
|
1 mēnesi atpakaļ |
Alexander Korolev
d1f10dd1e7
bench: r28 full rerun 159/176 — 155 vs 160 was run-to-run variance (8 flips), not a regression