bzuccaro/llama-watch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

spec: clarify All models datasource handling

Browse Source
This commit is contained in:
bzuccaro
2026-08-14 12:45:28 -06:00
parent e37d1360be
commit 93570dc9ba
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/superpowers/specs/2026-08-14-usage-stats-gpu-combos-design.md
+4 -2
View File
@@ -101,8 +101,10 @@ Two extensions to the existing llama-watch actions:
- `ui/inflight.html`: add "Display" select (`count`/`usage`) and "Primary - `ui/inflight.html`: add "Display" select (`count`/`usage`) and "Primary
stat" select. Both always visible; `primaryStat` has no effect in count stat" select. Both always visible; `primaryStat` has no effect in count
mode. Model datasource includes the `all` option (handled in the PI mode.
datasource provider if one exists, else the select defaults). - `src/lib/datasources.ts`: the `models` datasource prepends
`{ label: "All models", value: "all" }` to its items (so the model select
offers both the aggregate and individual models).
- `ui/gpu.html`: add "GPU combination (comma-separated ids)" textfield, - `ui/gpu.html`: add "GPU combination (comma-separated ids)" textfield,
optional, placeholder `e.g. 0,2`. optional, placeholder `e.g. 0,2`.