Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills / General / general-misc

inference_perf_hillclimb

Category: General  ·  Sub-category: general-misc  ·  Last updated:
Profiler-driven hill-climbing to close the inference throughput gap between TorchTitan's unified model (running inside vLLM) and vLLM's native model. Benchmark with generate.py --benchmark, climb optimization rungs (compile / cudagraph / fused kernels), profile torchtitan vs the native target, then patch the single biggest gap at a time and re-measure. Use when the user wants to benchmark or optimize RL inference generation speed, reproduce previous hill climbing study, or invokes /inference_perf_hillclimb.
Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

Close the gap between the TorchTitan unified model (in vLLM) and vLLM's native model on inference throughput, one profiler-found optimization at a time. Harness: torchtitan/experiments/rl/generate.py --benchmark. Append-only running log + full per-rung numbers live in torchtitan/experiments/rl/docs/inference_gap_ablation.md. Goal: match vLLM native 100%.

What this skill does

inference_perf_hillclimb is a community-contributed Claude Code skill in the general-misc sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/inference-perf-hillclimb/ and loads when your prompt matches the skill's trigger.

When to invoke it: Use when the user wants to benchmark or optimize RL inference generation speed, reproduce previous hill climbing study, or invokes /inference_perf_hillclimb.

Who uses this skill

The inference_perf_hillclimb Claude Code skill is built for Claude Code users and developers across all disciplines looking for general-purpose AI assistance. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 196,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/inference-perf-hillclimb
curl -L https://claudskills.com/skills/inference-perf-hillclimb/SKILL.md \
  -o ~/.claude/skills/inference-perf-hillclimb/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/inference-perf-hillclimb/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/inference-perf-hillclimb/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\inference-perf-hillclimb\SKILL.md on Windows. See the full install guide for step-by-step instructions.

Telegram

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

See pricing → Download desktop app

Frequently asked questions

How do I install the inference_perf_hillclimb Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/inference-perf-hillclimb/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the inference_perf_hillclimb skill do?
Profiler-driven hill-climbing to close the inference throughput gap between TorchTitan's unified model (running inside vLLM) and vLLM's native model. Benchmark with generate.py --benchmark, climb optimization rungs (compile / cudagraph / fused kernels), profile torchtitan vs the native target, then patch the single biggest gap at a time and re-measure. Use when the user wants to benchmark or optimize RL inference generation speed, reproduce previous hill climbing study, or invokes /inference_perf_hillclimb.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the inference_perf_hillclimb skill?
Use inference_perf_hillclimb when your Claude Code task falls under the General category — specifically in the general misc area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use inference_perf_hillclimb" or describe the task and let Claude pick). Browse related skills at /category/general/.
What is a Claude Code skill and how does the inference_perf_hillclimb skill fit in?
A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. inference_perf_hillclimb is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the General category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA
pytorch. (2026). inference_perf_hillclimb [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/inference-perf-hillclimb/
BibTeX
@misc{inference-perf-hillclimb-2026,
  author    = {pytorch},
  title     = {inference_perf_hillclimb [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/inference-perf-hillclimb/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge
[![ClaudSkills](https://claudskills.com/badge/inference-perf-hillclimb.svg)](https://claudskills.com/skills/inference-perf-hillclimb/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/inference-perf-hillclimb.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/inference-perf-hillclimb.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: inference_perf_hillclimb"></iframe>

Security scan

Grade A · scanned 2026-09-28 — free static scan against the OWASP Agentic Skills Top 10.

No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/inference-perf-hillclimb/#security)

Free. No spam. Unsubscribe in one click.

More General skills

Browse all General skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all General skills → Top 100 skills
Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills.  ·  What's New  ·  Install guide  ·  About  ·  llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore

Categories

Use cases

Popular tags

Learn

Site