Update model configurations and enhance LLM runtime logic

- Revised model URLs and descriptions in `llamacpp-models.example.yaml` and `ollama-models.example.yaml` to reflect new recommendations and vision capabilities.
- Updated the LLM runtime logic to support vision projectors and improved model resolution handling.
- Enhanced the installation script to conditionally include vision projectors when available.
- Added tests to validate the inclusion of vision projectors in model presets and ensure proper URL remapping for deprecated models.
- Improved documentation to clarify model usage and configuration options.
This commit is contained in:
Leonid Pershin
2026-08-21 07:40:47 +03:00
parent 618e6e4806
commit 15b95f04c7
7 changed files with 161 additions and 54 deletions
+15 -7
View File
@@ -478,13 +478,21 @@ def provision_llm(cfg: Config, host: str, log: Log) -> None:
f"{defaults[0].filename or gguf_filename_from_url(defaults[0].url)}"
)
if entries:
jobs = [
{
"url": e.url,
"filename": e.filename or gguf_filename_from_url(e.url),
}
for e in entries
]
jobs = []
for e in entries:
jobs.append(
{
"url": e.url,
"filename": e.filename or gguf_filename_from_url(e.url),
}
)
if e.mmproj_url:
jobs.append(
{
"url": e.mmproj_url,
"filename": gguf_filename_from_url(e.mmproj_url),
}
)
put_text(
cfg, host, "/tmp/gpu-rent-llamacpp-models.json", json.dumps(jobs, indent=2)
)