Automatically check for new upstream vllm releases and rebase the current fork branch onto the latest one. Orchestrates detect-upstream-base and rebase-assistant end-to-end. Use when the user asks to check for upstream updates, auto-rebase to the latest…
Detect the upstream vllm tag (v1) that the current branch is based on. Ensures the upstream remote is configured, fetches tags, and finds the nearest upstream tag reachable from the fork point. Use when you need to identify the upstream base version of the…
Set up a uv Python environment and install vLLM in editable mode from the current repo for NVIDIA CUDA GPUs. Use when the user asks to install vllm, set up a dev environment, create a virtualenv for vllm, or install a specific vllm release.
Run vLLM Buildkite CI-equivalent tests locally on NVIDIA GPUs using the current shell environment. Use when the user asks to run CI tests locally, reproduce CI failures, run a specific test file or test area, or match Buildkite test behavior.
Rebase custom fork commits onto a new upstream vllm tag, with conflict resolution and post-rebase verification via user-specified checks. Use when the user asks to rebase to a new upstream tag, update the fork base version, move custom patches to a newer vllm…