| .. |
|
2026-10-02_091915_kindling-4x-baseline.json
|
f944aea35c
kindling 4x: first full campaign — quality 166/176 (94/100, best on cluster), perf table, boot bugs ledger (spec-config form, UMA gate coin flip, control-file dirs); spec section + report artifacts (json+log snapshot, depth suite in flight)
|
3 недель назад |
|
2026-10-02_091915_kindling-4x-baseline.log
|
729f454eaa
kindling 4x: full campaign report package (md/json/log/manifest/recipe snapshot) — 94/100 quality, depth curve to 256K with no decode cliff (tg 60-88 t/s), TTFT 2.1s @256K c1
|
3 недель назад |
|
2026-10-02_091915_kindling-4x-baseline.manifest.json
|
729f454eaa
kindling 4x: full campaign report package (md/json/log/manifest/recipe snapshot) — 94/100 quality, depth curve to 256K with no decode cliff (tg 60-88 t/s), TTFT 2.1s @256K c1
|
3 недель назад |
|
2026-10-02_091915_kindling-4x-baseline.md
|
729f454eaa
kindling 4x: full campaign report package (md/json/log/manifest/recipe snapshot) — 94/100 quality, depth curve to 256K with no decode cliff (tg 60-88 t/s), TTFT 2.1s @256K c1
|
3 недель назад |
|
2026-10-02_091915_kindling-4x-baseline.recipe.toml
|
729f454eaa
kindling 4x: full campaign report package (md/json/log/manifest/recipe snapshot) — 94/100 quality, depth curve to 256K with no decode cliff (tg 60-88 t/s), TTFT 2.1s @256K c1
|
3 недель назад |
|
2026-10-02_103606_kindling-4x-27cf839.json
|
c2871f857a
kindling 4x re-bench on 27cf839 image (label kindling-4x-27cf839): 94/100 (166/176), identical to the a3c3a1d baseline — same fails TC-43/51/68/80, same depth curve. The megamoe #67 + spec-config #64 in the new image neither regress nor improve GLM-5.3-Flash 4x quality. Model now floats via refs/main (da920bb0 at bench time); manifest predates the models-field, so it carries no snapshot (next bench will).
|
3 недель назад |
|
2026-10-02_103606_kindling-4x-27cf839.log
|
c2871f857a
kindling 4x re-bench on 27cf839 image (label kindling-4x-27cf839): 94/100 (166/176), identical to the a3c3a1d baseline — same fails TC-43/51/68/80, same depth curve. The megamoe #67 + spec-config #64 in the new image neither regress nor improve GLM-5.3-Flash 4x quality. Model now floats via refs/main (da920bb0 at bench time); manifest predates the models-field, so it carries no snapshot (next bench will).
|
3 недель назад |
|
2026-10-02_103606_kindling-4x-27cf839.manifest.json
|
c2871f857a
kindling 4x re-bench on 27cf839 image (label kindling-4x-27cf839): 94/100 (166/176), identical to the a3c3a1d baseline — same fails TC-43/51/68/80, same depth curve. The megamoe #67 + spec-config #64 in the new image neither regress nor improve GLM-5.3-Flash 4x quality. Model now floats via refs/main (da920bb0 at bench time); manifest predates the models-field, so it carries no snapshot (next bench will).
|
3 недель назад |
|
2026-10-02_103606_kindling-4x-27cf839.md
|
c2871f857a
kindling 4x re-bench on 27cf839 image (label kindling-4x-27cf839): 94/100 (166/176), identical to the a3c3a1d baseline — same fails TC-43/51/68/80, same depth curve. The megamoe #67 + spec-config #64 in the new image neither regress nor improve GLM-5.3-Flash 4x quality. Model now floats via refs/main (da920bb0 at bench time); manifest predates the models-field, so it carries no snapshot (next bench will).
|
3 недель назад |
|
2026-10-02_103606_kindling-4x-27cf839.recipe.toml
|
c2871f857a
kindling 4x re-bench on 27cf839 image (label kindling-4x-27cf839): 94/100 (166/176), identical to the a3c3a1d baseline — same fails TC-43/51/68/80, same depth curve. The megamoe #67 + spec-config #64 in the new image neither regress nor improve GLM-5.3-Flash 4x quality. Model now floats via refs/main (da920bb0 at bench time); manifest predates the models-field, so it carries no snapshot (next bench will).
|
3 недель назад |
|
2026-10-02_135534_kindling4x-dgx14.json
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
3 недель назад |
|
2026-10-02_135534_kindling4x-dgx14.log
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
3 недель назад |
|
2026-10-02_135534_kindling4x-dgx14.manifest.json
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
3 недель назад |
|
2026-10-02_135534_kindling4x-dgx14.md
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
3 недель назад |
|
2026-10-02_135534_kindling4x-dgx14.recipe.toml
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
3 недель назад |
|
2026-10-02_160636_kindling4x-pluto.json
|
cad1944a7d
bench: kindling 4x + MiMo 4x kraken via pluto (wired) — WiFi-isolation campaign
|
3 недель назад |
|
2026-10-02_160636_kindling4x-pluto.log
|
cad1944a7d
bench: kindling 4x + MiMo 4x kraken via pluto (wired) — WiFi-isolation campaign
|
3 недель назад |
|
2026-10-02_160636_kindling4x-pluto.manifest.json
|
cad1944a7d
bench: kindling 4x + MiMo 4x kraken via pluto (wired) — WiFi-isolation campaign
|
3 недель назад |
|
2026-10-02_160636_kindling4x-pluto.md
|
cad1944a7d
bench: kindling 4x + MiMo 4x kraken via pluto (wired) — WiFi-isolation campaign
|
3 недель назад |
|
2026-10-02_160636_kindling4x-pluto.recipe.toml
|
cad1944a7d
bench: kindling 4x + MiMo 4x kraken via pluto (wired) — WiFi-isolation campaign
|
3 недель назад |
