vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

chore: retire asset-engine (Prime 2026-10-17); kuma gains delete-by-name; FleetTools/bootstrap/catalog marked

Browse Source
This commit is contained in:
vh
2026-10-17 00:16:31 -07:00
parent 055d56fa45
commit bc91b40ac5
8 changed files with 42 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/fleettools/inference.md
+9 -19
View File
@@ -1,4 +1,4 @@
# Direct inference seats + the Asset Engine control plane
# Direct inference seats
Most seats are vLLM behind the LiteLLM gateway — prefer the gateway
(`docs/fleettools/litellm.md`) unless you need something it does not expose.
@@ -8,30 +8,20 @@ Most seats are vLLM behind the LiteLLM gateway — prefer the gateway
```sh
# every fleet service, curated, with hrefs and descriptions
curl -s http://10.0.50.45:5100/api/services | python3 -m json.tool
# the inference control plane: what exists, what is up, GPU state
curl -s http://10.250.50.70:8200/api/v1/services
curl -s http://10.250.50.70:8200/api/v1/gpus
# the LLM roster
curl -s -H "Authorization: Bearer $KEY" http://10.250.50.70:4000/v1/models
```
Seats move between hosts and GPUs often enough that any transcribed table here would
mislead within a month.
## Asset Engine — `http://10.250.50.70:8200`
## Asset Engine — RETIRED 2026-10-17
Control plane over the PFI inference fleet. Can enumerate services, read GPU state,
**start and stop seats**, submit jobs and fetch assets.
```
GET /api/v1/services GET /api/v1/services/{id}/state
POST /api/v1/services/{id}/start POST /api/v1/services/{id}/stop
GET /api/v1/gpus POST /api/v1/jobs
GET /api/v1/assets/{id}/blob GET /api/v1/presets
```
⚠ **Liveness is keyed on the compose PROJECT name.** A seat reads OFFLINE unless the
compose project name equals the catalog's `lifecycle.stack`. Pin `name: <stack>` in
the compose file.
The control plane at `http://10.250.50.70:8200` is gone (Prime). Its last job was 2026-08-02, and every
catalog endpoint pointed at irv-ml1's dead wg0 address after the 09-06 mesh cutover. `docker compose
down` on ana-docker; the DB, image, repo (`vh/asset-engine`) and catalog (`docs/asset-engine/`) are kept, so
`docker compose up -d` in `/opt/docker/compose/asset-engine` brings it back. Start/stop a seat by hand
(`docker compose up -d` / `stop` in its compose dir on the GPU host).
## GPU hosts