Skip to content

feat(serving): add vLLM and llama.cpp alternatives - #4

Merged
rnckp merged 1 commit into
mainfrom
feature/inference
Jul 17, 2026
Merged

feat(serving): add vLLM and llama.cpp alternatives#4
rnckp merged 1 commit into
mainfrom
feature/inference

Conversation

@rnckp

@rnckp rnckp commented Jul 17, 2026

Copy link
Copy Markdown
Contributor

No description provided.

Copilot AI review requested due to automatic review settings July 17, 2026 11:54
@rnckp rnckp self-assigned this Jul 17, 2026
@rnckp
rnckp merged commit fa0d07a into main Jul 17, 2026
5 checks passed
@rnckp
rnckp deleted the feature/inference branch July 17, 2026 11:55

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds alternative local model-serving options (vLLM and llama.cpp) alongside Ollama by introducing lightweight launch helpers and documenting how to run the app against any OpenAI-compatible /v1 endpoint.

Changes:

  • Add scripts/serve-vllm.sh and scripts/serve-llamacpp.sh to start OpenAI-compatible servers with consistent defaults and env overrides.
  • Extend the Makefile with serve-* and run-* targets for vLLM and llama.cpp scenarios, wiring ports and model aliasing to config.yaml.
  • Update README.md and pyproject.toml wording to reflect OpenAI-compatible server support and provide usage guidance.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Show a summary per file
File Description
scripts/serve-vllm.sh New helper to run vLLM’s OpenAI-compatible server with configurable bind/port/alias and optional max context.
scripts/serve-llamacpp.sh New helper to run llama.cpp’s llama-server with configurable bind/port/alias and optional context size.
README.md Documents vLLM/llama.cpp as supported alternatives and adds Makefile-based run scenarios.
pyproject.toml Updates the package description to reflect OpenAI-compatible model server support.
Makefile Adds vLLM/llama.cpp serve/run targets and derives default model name from config.yaml.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread Makefile
@printf '%s\n' \
'make setup Install the locked Python environment' \
'make run-native Run the app locally with native Ollama' \
'make serve-vllm MODEL=… Serve a Hugging Face model with vLLM' \
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.

2 participants