TensorRT-LLM Inference
Orchestra-Research/AI-Research-SKILLs
Optimizes and serves LLMs on NVIDIA GPUs with TensorRT-LLM, covering quantization, in-flight batching, multi-GPU parallelism and the trtllm-serve command.
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence.
Install Aks GPU Inference
$ npx skills add microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/GitHub-Copilot-for-Azure aks-gpu-inference --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/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/aks-skills/skills/aks-gpu-inference .claude/skills/aks-gpu-inference && 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 "aks-gpu-inference" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inference into .claude/skills/aks-gpu-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aks-gpu-inference", 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/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inferenceType 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 microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/GitHub-Copilot-for-Azure aks-gpu-inference --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/aks-skills/skills/aks-gpu-inference .agents/skills/aks-gpu-inference && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "aks-gpu-inference" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inference into .agents/skills/aks-gpu-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aks-gpu-inference", 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 microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/GitHub-Copilot-for-Azure aks-gpu-inference --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/aks-skills/skills/aks-gpu-inference .cursor/skills/aks-gpu-inference && 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 "aks-gpu-inference" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inference into .cursor/skills/aks-gpu-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aks-gpu-inference", 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/microsoft/GitHub-Copilot-for-Azure.git --path plugins/aks-skills/skills/aks-gpu-inference--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 microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/GitHub-Copilot-for-Azure aks-gpu-inference --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/aks-skills/skills/aks-gpu-inference .gemini/skills/aks-gpu-inference && 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 "aks-gpu-inference" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inference into .gemini/skills/aks-gpu-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aks-gpu-inference", 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 microsoft/GitHub-Copilot-for-Azure aks-gpu-inferenceInstalls 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 microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/aks-skills/skills/aks-gpu-inference .github/skills/aks-gpu-inference && 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 "aks-gpu-inference" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inference into .github/skills/aks-gpu-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aks-gpu-inference", 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 microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/GitHub-Copilot-for-Azure aks-gpu-inference --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/aks-skills/skills/aks-gpu-inference .opencode/skills/aks-gpu-inference && 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 "aks-gpu-inference" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/plugins/aks-skills/skills/aks-gpu-inference into .opencode/skills/aks-gpu-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aks-gpu-inference", 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
aks-gpu-inference- GitHub stars
- 255
- Token cost
- ~764 tokens
- SKILL.md length
- 304 words
- Files
- 6 (incl. references)
- Skills in repo
- 61
- Repo updated
- First seen
- Licence
- MIT
At a glance
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence.
- Works in 6 steps: Bind subscription, cluster, kube… → Capture exact events/status and observed… → Route to scheduling, → …
- : setup (airunway-aks-setup)
- SKILL.md covers Quick Reference, When to Use This Skill, MCP Tools and Host Capability Gate, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Aks GPU Inference is an agent skill from microsoft/GitHub-Copilot-for-Azure, published by the product's own GitHub organization. Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/gpu-cost-and-scaling.md`, `references/gpu-observability.md` and `references/gpu-scheduling.md`).
It sits in AI & LLM Engineering, covering LLM inference and serving. It works with Microsoft Azure and NVIDIA AI Platform. The repository describes itself as: GitHub Copilot for Azure. The licence is MIT.
When your agent uses it
- : setup (airunway-aks-setup)
- Non-GPU incidents (aks-troubleshooting)
- Standalone VM quota (azure-quotas)
- Generic cost (cost-analysis
Example prompts
- “Insufficient nvidia.com/gpu”
- “/aks-gpu-inference”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Bind subscription, cluster, kube context, pool, and affected resource.
- Capture exact events/status and observed gpuProfile; state which reads ran.
- Route to scheduling,
- Separate container/host OOM from device-allocation failures. For OOMKilled,
- For KAITO not-ready, warn that Workspace deletion leaves its GPU pools;
- Report evidence, confidence, missing evidence, and owner handoff.
What it can do on your machine
Read from SKILL.md and the folder at commit ce94fce. 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
Aks GPU Inference loads about 764 tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 110 tokens; SKILL.md has 304 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
The full file from microsoft/GitHub-Copilot-for-Azure at commit ce94fce, republished under its MIT licence (© microsoft). 304 words, ~764 tokens.
Download SKILL.mdSave it as
.claude/skills/aks-gpu-inference/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- aks-gpu-inference
- description
- Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
- license
- MIT
- metadata.author
- Microsoft
- metadata.version
- 0.0.0-placeholder
AKS GPU Inference Day-2
Quick Reference
| Property | Value |
|---|---|
| Best for | AKS GPU/KAITO failures |
| Evidence | Bound target, events/status, gpuProfile, DCGM |
When to Use This Skill
Use for scheduling, VRAM/OOM, KAITO readiness, and workload scaling. Route exclusions as described above.
MCP Tools
Use a fitting host-advertised Azure read or the references' read-only queries.
Host Capability Gate
Before executing any referenced pipeline, verify that the host authorizes
the required shell and kubectl/az commands against the bound target.
File-backed collection also requires approved artifact storage and access to
any bundled files it uses. A governed Azure CLI tool alone does not establish
these capabilities. Equivalent host reads may replace commands only where
their advertised schemas provide the required evidence.
If execution is unavailable or prohibited, say so and analyze supplied or
redacted events, status, logs, and metrics, or give the operator a scoped
collection plan. State which reads did not run and leave conclusions requiring
missing evidence unconfirmed. Never route kubectl through Azure MCP or
bypass host policy. The authorization requirements below still apply.
Workflow
- Bind subscription, cluster, kube context, pool, and affected resource.
- Capture exact events/status and observed
gpuProfile; state which reads ran. - Route to scheduling, observability, KAITO, or scaling.
- Separate container/host OOM from device-allocation failures. For
OOMKilled, correlate container memory limits/usage and node conditions. For Managed+Install device-memory evidence, use the exporter on port 19400 and incident-windowFB_USED/FB_FREE; sizing tables do not establish a cause. - For KAITO not-ready, warn that Workspace deletion leaves its GPU pools; cleanup is separate and needs explicit authorization.
- Report evidence, confidence, missing evidence, and owner handoff.
Require explicit authorization before scaling, cordon/drain, deletion, add-on enablement, or monitoring mutation.
Error Handling
| Condition | Response |
|---|---|
| Missing/contradictory evidence | Mark unconfirmed; request the owner/read |
| Unknown profile | Preserve evidence; do not prescribe stack repair |
| Mutation required | Propose separately and wait for authorization |
© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in plugins/aks-skills/skills/aks-gpu-inference of microsoft/GitHub-Copilot-for-Azure.
- SKILL.md
- references/gpu-cost-and-scaling.md
- references/gpu-observability.md
- references/gpu-scheduling.md
- references/kaito-workspaces.md
- version.json
Open the folder on GitHubat commit ce94fce
Compare with similar skills
Aks GPU Inference 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 |
|---|---|---|---|---|---|---|
| Aks GPU Inference this skillmicrosoft/GitHub-Copilot-for-Azure | 255 | — | ~764 | Automated safety check: Pass | MIT | |
| TensorRT-LLM InferenceOrchestra-Research/AI-Research-SKILLs | 13k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Vllm Deploy Dockervllm-project/vllm-skills | 103 | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | |
| Dstack Prototypingdstackai/dstack | 2.3k | — | ~1.6k | Automated safety check: Pass | MPL-2.0 | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.2k | Automated safety check: Pass | Apache-2.0 | |
| LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~2.8k | Automated safety check: Pass | None |
Similar skills
Vllm Deploy Docker
vllm-project/vllm-skills
Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.
Dstack Prototyping
dstackai/dstack
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.
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.
LLM Torch Profiler Trace Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.
Integrate Model
tryonlabs/opentryon
Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).
More from microsoft/GitHub-Copilot-for-Azure
All 61 skills in this repo- Official
Capacity
microsoft/GitHub-Copilot-for-Azure
Discovers available Azure OpenAI model capacity across regions and projects.
- Official
Deploy Model
microsoft/GitHub-Copilot-for-Azure
Unified Azure OpenAI model deployment skill with intelligent intent-based routing.
- Official
Azure Storage
microsoft/GitHub-Copilot-for-Azure
Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake.
- Official
Microsoft Foundry
microsoft/GitHub-Copilot-for-Azure
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end.
- Official
Entra Agent Id
microsoft/GitHub-Copilot-for-Azure
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant)…
- Official
Azure Kubernetes Automatic Readiness
microsoft/GitHub-Copilot-for-Azure
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility.
Related
Works with
Categories
Questions about Aks GPU Inference
What does Aks GPU Inference do?
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. Aks GPU Inference is an agent skill from microsoft/GitHub-Copilot-for-Azure, published by the product's own GitHub organization. Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence.
When should I use Aks GPU Inference?
Aks GPU Inference fits situations like: : setup (airunway-aks-setup); non-GPU incidents (aks-troubleshooting); standalone VM quota (azure-quotas); generic cost (cost-analysis.
How do I install Aks GPU Inference in Claude Code?
Run `npx skills add microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a claude-code`. Or copy the skill folder (plugins/aks-skills/skills/aks-gpu-inference in microsoft/GitHub-Copilot-for-Azure) into .claude/skills/aks-gpu-inference in your project. Claude Code loads it when a task matches its description.
How do I install Aks GPU Inference in Codex?
Run `npx skills add microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a codex`. Or copy the skill folder (plugins/aks-skills/skills/aks-gpu-inference in microsoft/GitHub-Copilot-for-Azure) into .agents/skills/aks-gpu-inference in your project. Codex loads it when a task matches its description.
Can I use Aks GPU Inference 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 microsoft/GitHub-Copilot-for-Azure --skill aks-gpu-inference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aks-gpu-inference, .gemini/skills/aks-gpu-inference, .github/skills/aks-gpu-inference and .opencode/skills/aks-gpu-inference in your project.
What does Aks GPU Inference need to run?
SKILL.md names no scripts, command-line tools or credentials: Aks GPU Inference is instructions for the agent only.
Does Aks GPU Inference 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 Aks GPU Inference 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 Aks GPU Inference use?
Aks GPU Inference is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Aks GPU Inference use?
About 764 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.
What are the alternatives to Aks GPU Inference?
Skills that share tags, products or a category with Aks GPU Inference: TensorRT-LLM Inference (Orchestra-Research/AI-Research-SKILLs, 13k stars), Vllm Deploy Docker (vllm-project/vllm-skills, 103 stars), Dstack Prototyping (dstackai/dstack, 2.3k stars) and Graphsignal (graphsignal/graphsignal, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Aks GPU Inference?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/GitHub-Copilot-for-Azure, which has 255 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on October 9, 2026.
Source: microsoft/GitHub-Copilot-for-Azure on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.