Agent SkillsAtlasBETASign in
Back to directory

Multi Repo Qwen Setup

Agent skill
1 skill
READMEOverview ↓

Concrete qwen3-14B guide on NPU against the current worktree's simpler. Points at simpler's own in-repo qwen314bdecode example (zero cross-repo), then covers the two cross-repo paths — the pypto-serving runner (prefill/decode TPOT) and the pypto-lib decodefwd kernel (device decode TPOT + scheduler DFX). Defers cross-repo clone/install to multi-repo-setup, then gives the exact run commands (batch-1 and batch-16), the prefill ring/timeout gotchas that otherwise surface as 507018, how to read the per-token timing layers, and the kernel-level device-timing / swimlane flow. Invoke when running qwen3 on simpler, measuring decode/prefill TPOT, reproducing a qwen3 perf number, running qwen3 decodefwd device-timing or swimlane/overhead analysis, or chasing a 507018 on the qwen3 path.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryGeneralStars0

About this skill

Concrete qwen3-14B guide on NPU against the current worktree's simpler. Points at simpler's own in-repo qwen314bdecode example (zero cross-repo), then covers the two cross-repo paths — the pypto-serving runner (prefill/decode TPOT) and the pypto-lib decodefwd kernel (device decode TPOT + scheduler DFX). Defers cross-repo clone/install to multi-repo-setup, then gives the exact run commands (batch-1 and batch-16), the prefill ring/timeout gotchas that otherwise surface as 507018, how to read the per-token timing layers, and the kernel-level device-timing / swimlane flow. Invoke when running qwen3 on simpler, measuring decode/prefill TPOT, reproducing a qwen3 perf number, running qwen3 decodefwd device-timing or swimlane/overhead analysis, or chasing a 507018 on the qwen3 path.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 026cf645e7b947718ba3c811e882b9e7b1d2344dfb04420fb0048bcf8287c580

About scan coverage and limitations
Original listing metadata

Original name

multi-repo-qwen-setup

Original description

Concrete qwen3-14B guide on NPU against the current worktree's simpler. Points at simpler's own in-repo qwen3_14b_decode example (zero cross-repo), then covers the two cross-repo paths — the pypto-serving runner (prefill/decode TPOT) and the pypto-lib decode_fwd kernel (device decode TPOT + scheduler DFX). Defers cross-repo clone/install to multi-repo-setup, then gives the exact run commands (batch-1 and batch-16), the prefill ring/timeout gotchas that otherwise surface as 507018, how to read the per-token timing layers, and the kernel-level device-timing / swimlane flow. Invoke when running qwen3 on simpler, measuring decode/prefill TPOT, reproducing a qwen3 perf number, running qwen3 decode_fwd device-timing or swimlane/overhead analysis, or chasing a 507018 on the qwen3 path.

About this listing

Category
General
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
KEEP EXPLORING

Related packs & skills

Browse category →

Finding related packs and skills…

Multi Repo Qwen Setup | Agent Skills Atlas