Run any Skill in Manus with one click

upgrade-vllm

Stars8

Forks33

UpdatedJuly 17, 2026 at 20:24

Bump the pinned vLLM version in `pyproject.toml`, re-sync the upstream test plugin, and triage the breakages that the bump exposes. Use whenever a user asks to upgrade/bump/update vLLM, pull up the lower bound, or chase a specific upstream commit. Most failures after a bump are not in our code — they are upstream API churn (worker `load_model` wrappers, platform `is_*()` predicates, KV-cache layout flips, new constructor kwargs) that our `_enum = PlatformEnum.OOT` platform doesn't get the CPU/GPU short-circuits for.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

torch-spyre

torch-spyre/spyre-inference

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name

upgrade-vllm

description

Upgrade spyre-inference to the vLLM version specified by the user.

IMPORTANT: If the user hasn't specified a target version, ask them which version before proceeding.

Follow the complete procedure in docs/contributing/vllm-upgrade-procedure.md.

When you see {VERSION} in that document, replace it with the actual version number provided by the user (e.g., 0.23.0).

More from this repository

same repository

upgrade-vllm

torch-spyre/spyre-inference

2026-07-178

upgrade-torch-spyre

torch-spyre/spyre-inference

Bump the pinned `torch-spyre` git rev in `pyproject.toml` and update `spyre-rpms.lock` to match artifactory, binary-search to the latest commit that actually compiles against this host's `ibm-*` RPMs, clear the stale inductor cache, run a smoke test, and write a reviewer-ready PR description. Use whenever the user asks to "bump", "upgrade", "update", or "pull up" torch-spyre — typically after new `ibm-deeptools` / `ibm-flex` / `ibm-senlib` packages land that unblock previously-failing torch-spyre commits. Encodes that build failures are the expected signal that supporting libs need a matching bump, that the torchinductor cache must be wiped after the bump to avoid `TypeError: ...__init__() got an unexpected keyword argument ...` red herrings, and the curated PR-description shape (notable upstream PRs + bisect table + installed `ibm-*` RPM versions).

2026-07-148

cleanup-monthly-labels

torch-spyre/spyre-inference

Reconcile monthly labels (April2026, May2026, June2026, …) on the torch-spyre vLLM project board (project 2, view 7, repo torch-spyre/spyre-inference) at the end of each month. Use whenever the user asks to "clean up the board", "do the monthly label cleanup", "do the May/June/July cleanup", or otherwise refresh which monthly bucket each issue lives in. The skill enforces three rules — May-closed → MayYYYY, open MayYYYY → JuneYYYY swap, and Q2-relevant unlabeled issues → current month — while flagging anomalies for the user instead of guessing.

2026-06-238

debug-spyre

torch-spyre/spyre-inference

Debug numerical, compilation, or correctness failures anywhere the Spyre backend is involved — custom ops, attention, model runner, end-to-end vLLM runs. Use whenever a user reports failing Spyre tests, accuracy/tolerance mismatches against a CPU reference, torch.compile errors on `spyre` device, silent CPU fallbacks, or generally "something on Spyre is broken." Most bugs here are not in our code — they are torch-spyre op gaps or dtype/layout limitations, so debugging requires tracing into the torch-spyre site-packages, not just reading `spyre_inference/`. For attention-specific hints (cache-seeding, KV alignment, MHA/MQA, broadcast diagnosis), see `attention-notes.md` next to this file.

2026-06-018

Run any Skill with one click