Skill rating

Determine the correct behavior of vLLM's OpenAI-compatible or Anthropic-compatible API by checking the official upstream spec, instead of guessing from vLLM's own code. Use for any bug, issue, PR, rev

Playbook for changing vLLM's Transformers version bounds. Use when bumping the pinned or maximum Transformers version, raising the minimum Transformers version, or deleting vendored configs, processor

Time a vLLM model's forward pass on exact batch shapes (decode, prefill, chunked prefill, prefix hit, spec-decode verify, or mixes) with `vllm bench forward`, single-GPU or DP/TP/EP across nodes. Use

Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, ROCm/HIP, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and

Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation. Use when addi

Debug CUDA illegal memory access (IMA) errors in vLLM with CUDA core dumps and cuda-gdb. Use when a vLLM run crashes or hangs with a CUDA illegal memory access, device-side assert, or other asynchrono

Find vLLM deployment recipes and configs for LLMs and Hugging Face models by model and hardware. Use for recipe lookup, creation, and updates.

Fetch and diagnose vLLM Buildkite CI failure logs. Use when investigating failing CI jobs on a PR or build, when the user pastes a buildkite.com URL, or asks to fetch/diagnose CI logs.

Prepare a vLLM change for human PR review or re-review, or analyze an open pull request. Use before opening a PR, drafts included (e.g. `gh pr create`), or pushing review fixes, to check design fit, b