 Alexander Korolev
|
51b7404aa8
feat: serve --hf-cache <path> overrides the host-side HF cache dir per serve (config hf_cache_dir stays the global knob; mutual exclusion with --mirror)
|
4 周之前 |
|
Alexander Korolev
|
9431a65802
feat: r39 image lineage (lab tip 2026-09-21: new external-dep contract, DeepSelect, cutlass v4.7.1); fix deps.lock header continuation line not being a comment
|
1 月之前 |
|
Alexander Korolev
|
c11e975b4e
refactor: rename base image family to jovian-judgement (dir + images + profiles); tag = pin cut + model, :local retired
|
1 月之前 |
|
Alexander Korolev
|
8e20fd1dad
feat: versioned registry tags (build checksum) + latest; publish --push; duplicate guard via publication ledger with --force
|
1 月之前 |
|
Alexander Korolev
|
9c39603968
feat: [registry] — push built images to a registry (ghcr.io) after build; docker push via tmux on the node, localized (6 locales), --no-push opt-out
|
1 月之前 |
|
Alexander Korolev
|
69ba71ad59
feat: health probes [mikrotik] devices via RouterOS API login (ping = on, dead/rejected = off, blocking); power-on routes through on_entity relay
|
1 月之前 |
|
Alexander Korolev
|
3717c3a4de
feat: deps.lock — fetch-deps.sh verifies staged deps against a committed fingerprint lock (regen via --regen-lock / REGEN_LOCK=1)
|
1 月之前 |
|
Alexander Korolev
|
e3d6c0401b
feat: graceful MikroTik/RouterOS power-off via ROS API ([mikrotik] config)
|
1 月之前 |
|
Alexander Korolev
|
ed4bcc4369
2x re-cut: 512K context via max-num-seqs 4 + 10 GiB KV pin (bench 160/176)
|
1 月之前 |
|
Alexander Korolev
|
ed49b2d94a
docker: image sync falls back 200G→10G with a warning (fabric ssh fix hint)
|
1 月之前 |
|
Alexander Korolev
|
1b605f259b
docker: image sync inner hop over the fabric (ib_ip) when available
|
1 月之前 |
|
Alexander Korolev
|
20a3c768c9
agents: re-cut measured results + node-to-node transfer / hf-cache / pkill gotchas
|
1 月之前 |
|
Alexander Korolev
|
2f717631ff
report: stale cross-check of run ledger vs live probe (orange + runlock hint); new 'sm121 runlock list|close' offline ledger command
|
1 月之前 |
|
Alexander Korolev
|
07055b199f
web: recipes panel window — the report --serve page mounted at /recipes (one implementation, prefix-rewritten paths/SSE/viewer) + iframe theme inheritance; fix stale raw-window responses overwriting a newer selection; docs + playwright checks
|
1 月之前 |
|
Alexander Korolev
|
eb63d88c6b
add composed_model.local_files: hardlink node-local files into composed dir
|
1 月之前 |
|
Alexander Korolev
|
69690f0faf
web: topology map window — physical 2x4 GX10 grid, 200G/10G/DAC cables, HA glyphs, cluster frames; derive_topo from config facts; per-node HA plug states in probe
|
1 月之前 |
|
Alexander Korolev
|
1d73fd0945
serve/stop reliability + run ledger + archive curation
|
1 月之前 |
|
Alexander Korolev
|
081a0e6a0c
bench run package: per-run recipe copy + provenance manifest (recipe/config sha, launcher git sha, tool version, per-node image digest+build label); report shows provenance chip + Provenance column with drift flag
|
1 月之前 |
|
Alexander Korolev
|
48b7aa92f7
report: parent_model category field (medals/tree rank under base model); medals by parent x nodes (gold/silver/bronze, filterable); half-star grades (color bands 0-20/40/60/80, half-star precision, sort by absolute score, both-scores hint); report viewer page (rendered md + raw toggle, highlighted toml/json, recipe.toml section once per recipe, opens in new tab)
|
1 月之前 |
|
Alexander Korolev
|
2b94b23132
pin tool-eval-bench harness at 6be685f0e (dev65) + document cross-harness bias; extract Aiden DCP2 set (23 files, port assessment: 12 clean / 4 merge / 7 cherry-pick)
|
1 月之前 |
|
Alexander Korolev
|
f4abb53cbf
recipe [env] refs: values can resolve from recipe fields ({ from = "port" })
|
1 月之前 |
|
Alexander Korolev
|
15e9b62ca7
build: named version profiles (build_profile) + full r28 pin set (b12x 7216f6b9, lmcache 934c287a)
|
1 月之前 |
|
Alexander Korolev
|
448c3605f1
r18 16g 4x boot-verify passed; agents.md sm121-only rule; r28 4x dcp4 recipe (vllm pin override)
|
1 月之前 |
|
Alexander Korolev
|
1ef3eebed6
bench: add sm121 bench — tool-eval-bench with auto-landed reports; move stop handler to docker/stop
|
1 月之前 |
|
Alexander Korolev
|
a33cfa87a2
stop: wait until containers are actually stopped (60s verify); add --no-wait
|
1 月之前 |
|
Alexander Korolev
|
98dd4e42b3
bench instructions: keep json report (--json-file) alongside the md
|
1 月之前 |
|
Alexander Korolev
|
ccd615fcad
fix hardmode for night shift + future: version-pin tool (2.6.1.dev45, --hardmode = 88 scenarios), re-baseline anchor lane before gating; reports commit to recipes/<lane>/reports/; new eugr-4x test recipe (2x stays production default until 4x dramatic)
|
1 月之前 |
|
Alexander Korolev
|
1a6df4d3d8
AGENTS.md: use rg, not grep — recursive grep aborts/hangs in this tree
|
1 月之前 |
|
Alexander Korolev
|
bd72e30934
AGENTS.md: tool-eval-bench runs in a separate dir, never in this repo
|
1 月之前 |
 kilork
|
5ab8a05080
restore recipes/ in-tree — recipe + docker-images must share one revision
|
1 月之前 |
