noonghunna fbf6ab9022 fix(nvfp4): disable deepgemm on consumer cards

2026-07-07 22:05:09 +00:00

..

profiles

fix(nvfp4): disable deepgemm on consumer cards

2026-07-07 22:05:09 +00:00

bench-row-formatter.sh

refactor(launch): derive launcher tables from the registry + <engine>/default resolver

2026-05-26 18:35:35 +00:00

compose-meta.sh

chore(254): archive 15 Genesis/nightly composes + migrate the cascade [WIP: 5 test fixtures]

2026-06-05 13:37:48 +00:00

generate_compose.py

Pull gate: actionable messages for uncurated derives of curated models (#424)

2026-06-18 01:10:01 +05:00

gpu-select.sh

feat(estate): UUID-pin estate GPUs + placement assertion (#610 Phase A)

2026-07-07 01:02:48 +00:00

owui-register.sh

switch.sh --owui: auto-register a launched model in Open WebUI

2026-06-10 00:07:19 +00:00

owui-unregister.sh

Make the OWUI model picker scene-accurate (studio lanes + LLMs) (#470)

2026-06-25 05:22:05 +05:00

p2p-state.sh

p2p verdict: point WARN/INFO at docs/PCIE_P2P.md; doc catches up with the automated verdict

2026-07-05 00:10:57 +00:00

registry-emit.sh

Merge pull request #600 from noonghunna/feat/c3-catalog-weights-kv-columns

2026-07-07 02:37:24 +05:00

report_calib.sh

fix(#168): scope report.sh kv-calc calibration to the running model

2026-05-23 22:19:37 +00:00

studio-models.tsv

fix(studio): pull HiDream + Chroma weights in the ai-studio roster (#510) (#529)

2026-06-30 07:12:02 +05:00