Debug Cuda Crash
sgl-project/sglang
Call this skill when you need to debug CUDA crashes in SGLang using kernel API logging
Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X.
Install Hyperloom Remote Mn Qwen3 30b
$ npx skills add AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AMD-AGI/Hyperloom hyperloom-remote-mn-qwen3-30b --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/AMD-AGI/Hyperloom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b .claude/skills/hyperloom-remote-mn-qwen3-30b && 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 "hyperloom-remote-mn-qwen3-30b" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b into .claude/skills/hyperloom-remote-mn-qwen3-30b/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hyperloom-remote-mn-qwen3-30b", 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/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30bType 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 AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AMD-AGI/Hyperloom hyperloom-remote-mn-qwen3-30b --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b .agents/skills/hyperloom-remote-mn-qwen3-30b && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hyperloom-remote-mn-qwen3-30b" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b into .agents/skills/hyperloom-remote-mn-qwen3-30b/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hyperloom-remote-mn-qwen3-30b", 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 AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AMD-AGI/Hyperloom hyperloom-remote-mn-qwen3-30b --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b .cursor/skills/hyperloom-remote-mn-qwen3-30b && 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 "hyperloom-remote-mn-qwen3-30b" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b into .cursor/skills/hyperloom-remote-mn-qwen3-30b/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hyperloom-remote-mn-qwen3-30b", 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/AMD-AGI/Hyperloom.git --path docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b--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 AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AMD-AGI/Hyperloom hyperloom-remote-mn-qwen3-30b --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b .gemini/skills/hyperloom-remote-mn-qwen3-30b && 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 "hyperloom-remote-mn-qwen3-30b" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b into .gemini/skills/hyperloom-remote-mn-qwen3-30b/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hyperloom-remote-mn-qwen3-30b", 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 AMD-AGI/Hyperloom hyperloom-remote-mn-qwen3-30bInstalls 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 AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b .github/skills/hyperloom-remote-mn-qwen3-30b && 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 "hyperloom-remote-mn-qwen3-30b" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b into .github/skills/hyperloom-remote-mn-qwen3-30b/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hyperloom-remote-mn-qwen3-30b", 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 AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AMD-AGI/Hyperloom hyperloom-remote-mn-qwen3-30b --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b .opencode/skills/hyperloom-remote-mn-qwen3-30b && 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 "hyperloom-remote-mn-qwen3-30b" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b into .opencode/skills/hyperloom-remote-mn-qwen3-30b/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hyperloom-remote-mn-qwen3-30b", 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
hyperloom-remote-mn-qwen3-30b- GitHub stars
- 220
- Token cost
- ~1.8k tokens
- SKILL.md length
- 565 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X.
- AI & LLM Engineering work in your project
- SKILL.md covers Prerequisites, Workload A — Infera + PD…, Workload B — RayJob aggregated and Run notes
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Hyperloom Remote Mn Qwen3 30b is an agent skill from AMD-AGI/Hyperloom. Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X. Hand this skill to the agent to launch and monitor the run.
Its SKILL.md is about 1.8k 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. It works with Qwen and SGLang. The repository describes itself as: An agentic system that auto-optimizes LLM workloads on AMD GPUs.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/hyperloom-remote-mn-qwen3-30b”
What it can do on your machine
Read from SKILL.md and the folder at commit e5f2be1. 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
Hyperloom Remote Mn Qwen3 30b loads about 1.8k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 565 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 565 words (~1,827 tokens).
“Pinned workload for a remote multi-node optimize run. Pick one backend below and pass its FLAGS + Environment block to inference_optimizer optimize; the agent launches it in the background and monitors state.json until a terminal stop_reason — success (target_reached, global_converged…”
- name
- hyperloom-remote-mn-qwen3-30b
Files
Just SKILL.md in docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b of AMD-AGI/Hyperloom.
Open the folder on GitHubat commit e5f2be1
Compare with similar skills
Hyperloom Remote Mn Qwen3 30b 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 |
|---|---|---|---|---|---|---|
| Hyperloom Remote Mn Qwen3 30b this skillAMD-AGI/Hyperloom | 220 | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Debug Cuda Crashsgl-project/sglang | 37k | 2 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| LLM Pipeline Profiler AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 938 | — | ~3.9k | Automated safety check: Pass | None | |
| Clean Startup Logsgl-project/sglang | 37k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Model Architecture Diagram FinderBBuf/AI-Infra-Auto-Driven-SKILLS | 938 | — | ~1.2k | Automated safety check: Pass | None | |
| slime RL Post-TrainingOrchestra-Research/AI-Research-SKILLs | 13k | 4 repos | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
LLM Pipeline Profiler Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Breaks LLM torch profiler traces down by forward pass, layer and kernel, with timing tables and Perfetto time ranges for the layers you want to inspect.
Clean Startup Log
sgl-project/sglang
Audit SGLang startup logs, save evidence, and propose cleanup for user review.
Model Architecture Diagram Finder
BBuf/AI-Infra-Auto-Driven-SKILLS
Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.
slime RL Post-Training
Orchestra-Research/AI-Research-SKILLs
Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.
Generate Profile
sgl-project/sglang
Generate an e2e profiling trace of an SGLang server run. An agent skill from sgl-project/sglang.
More from AMD-AGI/Hyperloom
Critic Agent
AMD-AGI/Hyperloom
Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom.
Review PR
AMD-AGI/Hyperloom
Review a Hyperloom pull request. An agent skill from AMD-AGI/Hyperloom.
Hyperloom Global Kb
AMD-AGI/Hyperloom
Deploys or restarts the shared global Experience KB that Hyperloom workspaces push their Experiences to and pull others' from, validates authenticated health, and tells each workspace which .env…
Hyperloom Setup
AMD-AGI/Hyperloom
Configures Hyperloom after pip install --target . An agent skill from AMD-AGI/Hyperloom.
Related
Categories
Questions about Hyperloom Remote Mn Qwen3 30b
What does Hyperloom Remote Mn Qwen3 30b do?
Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X. Hyperloom Remote Mn Qwen3 30b is an agent skill from AMD-AGI/Hyperloom. Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X.
When should I use Hyperloom Remote Mn Qwen3 30b?
Hyperloom Remote Mn Qwen3 30b fits situations like: AI & LLM Engineering work in your project.
How do I install Hyperloom Remote Mn Qwen3 30b in Claude Code?
Run `npx skills add AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a claude-code`. Or copy the skill folder (docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b in AMD-AGI/Hyperloom) into .claude/skills/hyperloom-remote-mn-qwen3-30b in your project. Claude Code loads it when a task matches its description.
How do I install Hyperloom Remote Mn Qwen3 30b in Codex?
Run `npx skills add AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a codex`. Or copy the skill folder (docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b in AMD-AGI/Hyperloom) into .agents/skills/hyperloom-remote-mn-qwen3-30b in your project. Codex loads it when a task matches its description.
Can I use Hyperloom Remote Mn Qwen3 30b 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 AMD-AGI/Hyperloom --skill hyperloom-remote-mn-qwen3-30b -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hyperloom-remote-mn-qwen3-30b, .gemini/skills/hyperloom-remote-mn-qwen3-30b, .github/skills/hyperloom-remote-mn-qwen3-30b and .opencode/skills/hyperloom-remote-mn-qwen3-30b in your project.
What does Hyperloom Remote Mn Qwen3 30b need to run?
SKILL.md names no scripts, command-line tools or credentials: Hyperloom Remote Mn Qwen3 30b is instructions for the agent only.
Does Hyperloom Remote Mn Qwen3 30b 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 Hyperloom Remote Mn Qwen3 30b 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 Hyperloom Remote Mn Qwen3 30b use?
Hyperloom Remote Mn Qwen3 30b has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Hyperloom Remote Mn Qwen3 30b use?
About 1.8k tokens (SKILL.md is roughly 7.3k 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 Hyperloom Remote Mn Qwen3 30b?
Skills that share tags, products or a category with Hyperloom Remote Mn Qwen3 30b: Debug Cuda Crash (sgl-project/sglang, 37k stars), LLM Pipeline Profiler Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 938 stars), Clean Startup Log (sgl-project/sglang, 37k stars) and Model Architecture Diagram Finder (BBuf/AI-Infra-Auto-Driven-SKILLS, 938 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hyperloom Remote Mn Qwen3 30b?
AMD-AGI (a GitHub organization) maintains it in AMD-AGI/Hyperloom, which has 220 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.
Source: AMD-AGI/Hyperloom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.