Frank
a5fe045b58
Structural repair: - 13 pages were the same document twice (each exactly 2x its HEAD size), a second frontmatter block whose closing fence had been glued onto a body line by a frontmatter rewrite that re-read its own output. Un-doubled by cutting at the second frontmatter and keeping the copy whose body is a superset; the orphan census reports 0 lost tokens against HEAD. - log.md: one entry per date, bare `## YYYY-MM-DD` headings, newest first — 66 dated headings merged into 34, titles demoted to bold leads, every content line verified present. The file had been descending at the head and ascending at the tail. Ownership moves: - New `LLM/frank-medium.md` is the locator for the retired Dankserver endpoint: era windows quoted from each era page's own banner, no numbers restated, and the two unresolved date conflicts recorded instead of silently resolved. `frank-archon.md` links to it instead of restating the pre-rename window. - The four Pipeline-Parallelism stubs (frontmatter only, no body) are gone; `Multi-Node Runtimes.md` owns runtime construction, launch, mixed-vendor verdicts and cross-split spec decode, and the four links that pointed at the stubs were repointed at it or at the drafter page. - Authentik's three stub pages fold into `Authentik.md`, with the process detail and the outpost reference split out so the parent stays under the length hint. Verified corrections (host census + live probe, 2026-10-19): - The MXFP4 checkpoint two pages called the "on-disk rollback" is gone: /home/dank/models/ holds StillDeadcode, rad and tpl.jinja. Stated once, on the era page that owns that payload; the swap page now links to it. - frank-medium-radiance-mxfp4: the 4.24/7 accept rate belongs to the DFlash2 arm measured on the FP8 target, not to the MXFP4 era; the 3-family soak run census is kept once (155 requests) instead of twice (~120 and 155). - Fleet shapes re-confirmed against the live endpoints before touching any page: 3x200000 fp8 KV, 2x200704, 2x262144. Index rows are regenerated, not hand-carved. Net -1,849 vault lines.
1.4 KiB
1.4 KiB
Operations
Procedures for operating the fleet. The LLM-specific pages live under
LLM; infrastructure and architecture under the
../Infrastructure/ and ../Architecture/ folders.
- Remote Job Runner — Detached long jobs with sentinel files: why tail-watchers fail structurally, the script, its invariants, verification.
- Payload and Disk Reclaim — Disk pressure procedure: measure every bucket, classify, prove nothing references the payload, stage, purge on approval.
- Container Host Reachability — Two reachability quirks: containers cannot dial unpublished host ports, and netns membership decides reachability.
- Fleet Ops Playbook — Incident-shaped procedures: endpoint down with a GPU holder, stop-first bench windows, service iteration, waking a host.
- Fleet Audit and Posture — Three standing audits: monitoring completeness, vhost proxy health, and behavioural security posture.
- SSH and Remote Access — Passwordless SSH bootstrap without sshpass, remote execution against fish login shells, and frozen-GUI triage.
Related
- Observability Provisioning — monitoring config as code
- Deploy State Triage — the deploy plumbing
- Quadlet Lifecycle — the unit layer