Skip to main content

ai-dynamo/aiconfigurator

SkillsMP has collected 4 skills from ai-dynamo/aiconfigurator. Open a skill to review its source and details.

Latest recorded source activity
SkillsMP catalog refreshed
skills collected
4
GitHub stars
407
GitHub forks
151

Skills in this repository

1 occupation categories · 100% classified

Showing 4 of 4 collected skills.

occupation
Software Developers
description

Convert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests. Use when adapting server configuration, checking whether a recipe can be estimated, generating canonical…

updated
occupation
Software Developers
description

Use when validating AIC predictions against real GPU serving measurements and root-causing fidelity gaps (prediction-vs-measured issues, memory/concurrency mismatches, per-op latency divergence). Covers dummy-weight methodology, measurement parity traps,…

updated
occupation
Software Developers
description

Use when running long AIC/aiconfigurator GPU perf auto-collection for a specific GPU/framework/framework_version, including draft-PR checkpoints, resumable collect_xx.py runs, framework-version/kernel preflight, collector fixes/skips, special runtime images,…

updated
occupation
Software Developers
description

Design, add, review, or modify AIC Collector operations and their case population. Use for new Collector ops, backend registry entries, collector/cases YAML, case generators/getters, pruning or deduplication, persisted perf keys, framework-version routing,…

updated
Showing 4 of 4 collected skills.