wylab/llama-swap
1
0
Fork 1
mirror of https://github.com/mostlygeek/llama-swap.git synced 2026-09-07 16:37:22 +02:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity
581 Commits 3 Branches 200 Tags
v253
Commit Graph
2 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
David SoušekGitHubDavid Soušek
 		32c3d66cd3 config,server: add startup profile hook (#1053)
Validate JSON Schema / validate-schema (push) Successful in 45s
Details
Linux CI / run-tests (push) Failing after 2m34s
Details
Windows CI / run-tests (push) Canceled after 0s
Details 
An optional `hooks.on_startup.profile` setting for activating a profile
on startup and after a configuration reload:

```yaml
profiles:
  coding:
    pins:
      llm-code: "gpt-oss-120b"

hooks:
  on_startup:
    profile: "coding"
```

Another attempt to close #992 after unsuccessful #993 ;)

Co-authored-by: David Soušek <david.sousek@intelogy.co.uk>
 2026-08-29 11:26:54 -07:00
David SoušekGitHubDavid Soušek
 		3e3646f9f9 perf: ignore LACT devices reporting zero VRAM (#753)
Linux CI / run-tests (push) Successful in 2m58s
Details
Windows CI / run-tests (push) Has been cancelled
Details 
Ignore LACT devices that report zero total VRAM.

Some virtual GPUs on headless VMs report `MemTotalMB == 0` through LACT,
which makes them appear in performance monitoring despite not providing
useful memory data. Skip those entries so only usable GPU devices are
reported.

This makes performance monitoring cleaner on headless VMs with virtual
GPUs that report zero VRAM.

Co-authored-by: David Soušek <david.sousek@intelogy.co.uk>
 2026-05-13 10:03:54 -07:00