How do I install the Optimize LLM Inference skill?

Run npx skillmds@latest add hiteshbandhu/optimize-llm-inference in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Optimize LLM Inference safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Optimize LLM Inference?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Optimize LLM Inference free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Optimize LLM Inference?

hiteshbandhu (@hiteshbandhu) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Optimize LLM Inference by hiteshbandhu

Name: Optimize LLM Inference
Author: hiteshbandhu

Optimize LLM Inference

Runs workflows for GPU/inference talks — Groq LPU latency, OSS inference stacks, MoE networking, serverless fine-tune, frontier cluster design, Devin agent infra, Gemma sizing. Use when optimizing inference $/token, training networks, or picking open models.

hiteshbandhu Updated Sep 17, 2026

File contents

Optimize LLM inference

Action playbook from eight AI Engineer / World's Fair talks. Do not summarize talks — pick a workflow and execute it.

Supporting files (read when needed):

workflows.md — workflows A–G (steps, deliverables, stop conditions)
source-index.md — src-NNN → talk learnings in ingest-into-skills

Optional: {SKILL_OUTPUT_DIR}/optimize-llm-inference/

Step 0 — Pick workflow

Use the decision tree below. Open the matching section in workflows.md.

What is the user trying to do?
├─ Ultra-low-latency inference (LPU/Groq-class)         → A
├─ Production OSS inference (quantization/routing)      → B
├─ MoE training network topology                        → C
├─ Fast fine-tune experiment loops                      → D
├─ Frontier cluster / SemiAnalysis planning               → E
├─ Coding agent infra (Devin-style)                     → F
└─ Pick open model tier (Gemma)                         → G

Stop summarizing once a workflow is identified — run its checklist.

Install

cp -r skills/optimize-llm-inference ~/.claude/skills/
cp -r skills/optimize-llm-inference ~/.cursor/skills/
cp -r skills/optimize-llm-inference ~/.codex/skills/

From skills-i-use or ingest-into-skills (playlists/gpus-inference-aie-world-s-fair-2024/).

Cross-cutting rules

Rule	Source
Measure $/token at your concurrency	[src-002 @ 10:24]
Network matters for MoE more than GPU count	[src-003 @ 7:56]
Right-size model per route	[src-002 @ 2:07]

Disputed steps: see source-index.md. Name workflow A–G; save artifacts to ./skill-outputs/optimize-llm-inference/ when requested; do not auto-commit.

Invocation examples

@optimize-llm-inference compare inference $/token
MoE cluster network design

---name: optimize-llm-inferencedescription: Runs workflows for GPU/inference talks — Groq LPU latency, OSS inference stacks, MoE networking, serverless fine-tune, frontier cluster design, Devin agent infra, Gemma sizing. Use when optimizing inference $/token, training networks, or picking open models.---# Optimize LLM inferenceAction playbook from eight AI Engineer / World's Fair talks. **Do not summarize talks** — pick a workflow and execute it.**Supporting files** (read when needed):- [workflows.md](workflows.md) — workflows A–G (steps, deliverables, stop conditions)- [source-index.md](source-index.md) — src-NNN → talk learnings in ingest-into-skillsOptional: `{SKILL_OUTPUT_DIR}/optimize-llm-inference/`---## Step 0 — Pick workflowUse the decision tree below. Open the matching section in [workflows.md](workflows.md).```What is the user trying to do?├─ Ultra-low-latency inference (LPU/Groq-class) → A├─ Production OSS inference (quantization/routing) → B├─ MoE training network topology → C├─ Fast fine-tune experiment loops → D├─ Frontier cluster / SemiAnalysis planning → E├─ Coding agent infra (Devin-style) → F└─ Pick open model tier (Gemma) → G```**Stop summarizing** once a workflow is identified — run its checklist.---## Install```bashcp -r skills/optimize-llm-inference ~/.claude/skills/cp -r skills/optimize-llm-inference ~/.cursor/skills/cp -r skills/optimize-llm-inference ~/.codex/skills/```From [skills-i-use](https://github.com/hiteshbandhu/skills-i-use) or ingest-into-skills (`playlists/gpus-inference-aie-world-s-fair-2024/`).---## Cross-cutting rules| Rule | Source ||------|--------|| Measure $/token at your concurrency | [src-002 @ 10:24] || Network matters for MoE more than GPU count | [src-003 @ 7:56] || Right-size model per route | [src-002 @ 2:07] |Disputed steps: see [source-index.md](source-index.md). Name workflow A–G; save artifacts to `./skill-outputs/optimize-llm-inference/` when requested; do not auto-commit.---## Invocation examples```@optimize-llm-inference compare inference $/tokenMoE cluster network design```

Frequently asked questions