engine-performance

engine-performance is an MLOps & model serving skill for AI agents, published by scragnog in the HOT-Step-CPP repository on GitHub. Skillspace rates engine-performance D (68/100) and it passed the safety scan; the rating is based on static analysis only.

Explains where HOT-Step generation time goes (LM/DiT/VAE), how the TensorRT paths activate, how to benchmark from logs, and which knobs trade quality for speed. Use when profiling slow generations, working on dit-trt.h/lm-trt.h/adapter-trt.h/hot-step-sampler-trt.h, debugging TRT/ONNX issues, or deciding what performance work is DONE vs PLANNED.

Grade
D
Quality
68 / 100
Safety
Passed
GitHub stars
78

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubscragnog/HOT-Step-CPP

Our review

Architecture
96 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in MLOps & model serving

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.