vllm-ascend-performance-regression · git:20260911.9f92063 · 2026-09-11 · sha256 f390dfefd6f7122a

vllm-ascend-performance-regression git:20260911.9f92063A

Immutable. This exact content is served forever at /api/v1/blob/f390dfefd6f7122a.

---
name: "vllm-ascend-performance-regression"
description: "Plan, record, and analyze controlled baseline-versus-candidate vLLM Ascend serving performance experiments with isolated sessions, identical non-code configuration, alternating A/B order, warmup exclusion, variance and outlier reporting, and metric-specific regression thresholds. Use for throughput, TTFT, TPOT, ITL, acceptance-rate, startup-time, or HBM regression checks. Do not use for correctness, single-state measurement, HBM component attribution, or profiling root-cause analysis."
---

<!-- Generated from .agents/skills/vllm-ascend-performance-regression/SKILL.md. Do not edit. -->

# vllm-ascend-performance-regression

Read `.agents/skills/vllm-ascend-performance-regression/SKILL.md` and only the references needed
for the current task. The canonical skill owns the workflow.