Skip to content

feat(dev): add local vLLM model helper#212

Draft
binaryaaron wants to merge 1 commit into
mainfrom
binaryaaron/add-vllm-debug
Draft

feat(dev): add local vLLM model helper#212
binaryaaron wants to merge 1 commit into
mainfrom
binaryaaron/add-vllm-debug

Conversation

@binaryaaron

@binaryaaron binaryaaron commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

Summary\n- add an optional Linux local-models dependency group for vLLM\n- add a source-tree helper to discover cached models, serve them, and probe OpenAI-compatible endpoints\n- document GPU-host setup, local credentials, and Anonymizer provider configuration\n- redact resolved API keys from serve --dry-run output\n\n## Validation\n- uv lock --check\n- 7 focused helper tests\n- Ruff check and format check\n- copyright check\n- strict MkDocs build\n- full local suite: 1090 passed; the remaining /dev/null ownership test also fails on current main in this environment

Signed-off-by: Aaron Gonzales <aagonzales@nvidia.com>
@binaryaaron binaryaaron force-pushed the binaryaaron/add-vllm-debug branch from da1d319 to a3a8702 Compare July 13, 2026 21:50
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant