Quark Torch Quant Perf
amd/Quark
Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.
Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators.
Install LLM Inference Batching Scheduler
$ npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering llm-inference-batching-scheduler --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/llm-inference-batching-scheduler .claude/skills/llm-inference-batching-scheduler && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "llm-inference-batching-scheduler" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-scheduler into .claude/skills/llm-inference-batching-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-inference-batching-scheduler", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-schedulerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering llm-inference-batching-scheduler --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/llm-inference-batching-scheduler .agents/skills/llm-inference-batching-scheduler && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "llm-inference-batching-scheduler" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-scheduler into .agents/skills/llm-inference-batching-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-inference-batching-scheduler", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering llm-inference-batching-scheduler --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/llm-inference-batching-scheduler .cursor/skills/llm-inference-batching-scheduler && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "llm-inference-batching-scheduler" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-scheduler into .cursor/skills/llm-inference-batching-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-inference-batching-scheduler", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lazyFrogLOL/Harness_Engineering.git --path skills/llm-inference-batching-scheduler--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering llm-inference-batching-scheduler --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/llm-inference-batching-scheduler .gemini/skills/llm-inference-batching-scheduler && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "llm-inference-batching-scheduler" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-scheduler into .gemini/skills/llm-inference-batching-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-inference-batching-scheduler", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lazyFrogLOL/Harness_Engineering llm-inference-batching-schedulerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/llm-inference-batching-scheduler .github/skills/llm-inference-batching-scheduler && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "llm-inference-batching-scheduler" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-scheduler into .github/skills/llm-inference-batching-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-inference-batching-scheduler", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering llm-inference-batching-scheduler --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/llm-inference-batching-scheduler .opencode/skills/llm-inference-batching-scheduler && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "llm-inference-batching-scheduler" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/llm-inference-batching-scheduler into .opencode/skills/llm-inference-batching-scheduler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-inference-batching-scheduler", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
llm-inference-batching-scheduler- GitHub stars
- 128
- Token cost
- ~2.2k tokens
- SKILL.md length
- 822 words
- Files
- 1
- Skills in repo
- 32
- Repo updated
- First seen
- Licence
- None found
At a glance
Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators.
- Works in 3 steps: Mathematical Analysis (Before Any Code) → Systematic Parameter Search → Implementation with Invariant Checking
- Tasks involving batch planning
- SKILL.md covers When to Apply This Skill, Core Concepts, Systematic Approach and Common Pitfalls and Mitigations, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
LLM Inference Batching Scheduler is an agent skill from lazyFrogLOL/Harness_Engineering. Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators. This skill applies when optimizing request batching to minimize cost while meeting latency thresholds, particularly when dealing with shape compilation costs, padding overhead, and multi-bucket request distributions. Use this skill for tasks involving batch planning, shape selection, generation-length bucketing, and cost-model-driven optimization for neural network inference.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM inference and serving and Deep learning.
When your agent uses it
- Tasks involving batch planning
- Shape selection
- Generation-length bucketing
- Cost-model-driven optimization for neural network inference
Example prompts
- “/llm-inference-batching-scheduler”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
- Mathematical Analysis (Before Any Code)
- Systematic Parameter Search
- Implementation with Invariant Checking
What it can do on your machine
Read from SKILL.md and the folder at commit cae3b25. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
LLM Inference Batching Scheduler loads about 2.2k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 822 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 822 words (~2,202 tokens).
“This skill provides systematic approaches for designing batching schedulers that optimize LLM inference workloads on compilation-based accelerators (TPUs, custom ASICs). The core challenge involves balancing multiple competing objectives: minimizing compilation cost (fewer shapes), reducing padding waste (tighter batches), and meeting…”
- name
- llm-inference-batching-scheduler
Files
Just SKILL.md in skills/llm-inference-batching-scheduler of lazyFrogLOL/Harness_Engineering.
Open the folder on GitHubat commit cae3b25
Compare with similar skills
LLM Inference Batching Scheduler next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LLM Inference Batching Scheduler this skilllazyFrogLOL/Harness_Engineering | 128 | — | ~2.2k | Automated safety check: Pass | None | |
| Quark Torch Quant Perfamd/Quark | 182 | — | ~3k | Automated safety check: Pass | MIT | |
| RWKV Architecture GuideOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~1.8k | Automated safety check: Pass | MIT | |
| ML Engineerdavila7/claude-code-templates | 33k | 9 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Databricks ML Trainingdatabricks/databricks-agent-skills | 345 | — | ~4.6k | Automated safety check: Pass | Custom licence | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
RWKV Architecture Guide
Orchestra-Research/AI-Research-SKILLs
Explains RWKV, a hybrid that trains in parallel like a GPT and runs inference like an RNN with constant memory per token, plus usage, fine-tuning and troubleshooting.
ML Engineer
davila7/claude-code-templates
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks.
- Official
Databricks ML Training
databricks/databricks-agent-skills
Train ML models on Databricks. An agent skill from databricks/databricks-agent-skills.
Graphsignal
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
Model Builder
qualcomm/qai-appbuilder
QAI ModelBuilder. An agent skill from qualcomm/qai-appbuilder.
More from lazyFrogLOL/Harness_Engineering
All 32 skills in this repoChess Best Move
lazyFrogLOL/Harness_Engineering
Guide for analyzing chess positions from images and determining optimal moves.
Crack 7z Hash
lazyFrogLOL/Harness_Engineering
This skill provides guidance for cracking 7z archive password hashes.
Distribution Search
lazyFrogLOL/Harness_Engineering
Guidance for finding probability distributions that satisfy specific statistical constraints such as KL divergence targets, entropy requirements, or moment conditions.
Feal Linear Cryptanalysis
lazyFrogLOL/Harness_Engineering
This skill provides guidance for FEAL cipher linear cryptanalysis tasks.
Gcode To Text
lazyFrogLOL/Harness_Engineering
Decode and interpret text content from G-code files by analyzing toolpath geometry and coordinate patterns.
Gpt2 Codegolf
lazyFrogLOL/Harness_Engineering
Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints.
Related
Categories
Questions about LLM Inference Batching Scheduler
What does LLM Inference Batching Scheduler do?
Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators. LLM Inference Batching Scheduler is an agent skill from lazyFrogLOL/Harness_Engineering. Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators.
When should I use LLM Inference Batching Scheduler?
LLM Inference Batching Scheduler fits situations like: tasks involving batch planning; shape selection; generation-length bucketing; cost-model-driven optimization for neural network inference.
How do I install LLM Inference Batching Scheduler in Claude Code?
Run `npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a claude-code`. Or copy the skill folder (skills/llm-inference-batching-scheduler in lazyFrogLOL/Harness_Engineering) into .claude/skills/llm-inference-batching-scheduler in your project. Claude Code loads it when a task matches its description.
How do I install LLM Inference Batching Scheduler in Codex?
Run `npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a codex`. Or copy the skill folder (skills/llm-inference-batching-scheduler in lazyFrogLOL/Harness_Engineering) into .agents/skills/llm-inference-batching-scheduler in your project. Codex loads it when a task matches its description.
Can I use LLM Inference Batching Scheduler in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lazyFrogLOL/Harness_Engineering --skill llm-inference-batching-scheduler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/llm-inference-batching-scheduler, .gemini/skills/llm-inference-batching-scheduler, .github/skills/llm-inference-batching-scheduler and .opencode/skills/llm-inference-batching-scheduler in your project.
What does LLM Inference Batching Scheduler need to run?
SKILL.md names no scripts, command-line tools or credentials: LLM Inference Batching Scheduler is instructions for the agent only.
Does LLM Inference Batching Scheduler access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is LLM Inference Batching Scheduler safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does LLM Inference Batching Scheduler use?
No licence was found for LLM Inference Batching Scheduler or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does LLM Inference Batching Scheduler use?
About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to LLM Inference Batching Scheduler?
Skills that share tags, products or a category with LLM Inference Batching Scheduler: Quark Torch Quant Perf (amd/Quark, 182 stars), RWKV Architecture Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), ML Engineer (davila7/claude-code-templates, 33k stars) and Databricks ML Training (databricks/databricks-agent-skills, 345 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LLM Inference Batching Scheduler?
lazyFrogLOL (a GitHub user) maintains it in lazyFrogLOL/Harness_Engineering, which has 128 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on May 18, 2026.
Source: lazyFrogLOL/Harness_Engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.