New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Build Vllm Onednn Zendnn

by amd in amd/ZenDNN

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

Custom licenceAuto-check passedAI & LLM Engineering

Install Build Vllm Onednn Zendnn

skills CLI
$ npx skills add amd/ZenDNN --skill build-vllm-onednn-zendnn -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install amd/ZenDNN build-vllm-onednn-zendnn --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/amd/ZenDNN.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/build-vllm-onednn-zendnn .claude/skills/build-vllm-onednn-zendnn && rm -rf skills-src

Use ~/.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/

Facts

Skill name
build-vllm-onednn-zendnn
GitHub stars
158
Token cost
~5.2k tokens
SKILL.md length
2,323 words
Files
5
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

  • Works in 6 steps: Stage 0 — Confirm inputs. Resolve the… → Stage 1 — ZenDNN native lib. **Invoke… → Stage 2 — oneDNN source prep (NO build).… → …
  • Asked to build vLLM CPU against oneDNN/ZenDNN
  • SKILL.md covers FAILURE POLICY (applies to…, Sections, Flow and Inputs to confirm, plus 4 more sections
  • Runs Shell scripts from its folder; calls git, pip and bash; reaches github.com and download.pytorch.org

What it does

Build Vllm Onednn Zendnn is an agent skill from amd/ZenDNN. Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch). Use when asked to build vLLM CPU against oneDNN/ZenDNN or produce a ZenDNN-enabled vLLM wheel. Orchestrates the ZenDNN native lib (via the build-zendnn skill), upstream oneDNN source prep, a conda build env, the vLLM build, and two-tier verification.

Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `build_wheel.sh` and `create_env.sh`).

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with vLLM and C++.

When your agent uses it

  • Asked to build vLLM CPU against oneDNN/ZenDNN
  • Produce a ZenDNN-enabled vLLM wheel

Example prompts

  • “/build-vllm-onednn-zendnn”

Requirements

  • A Bash shell

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Stage 0 — Confirm inputs. Resolve the inputs above with the user
  2. Stage 1 — ZenDNN native lib. **Invoke the existing build-zendnn
  3. Stage 2 — oneDNN source prep (NO build). Use **upstream
  4. Stage 3 — Conda build env. Drive this with the bundled
  5. Stage 4 — vLLM build. Drive this with the bundled build_wheel.sh
  6. Stage 5 — Verification (BOTH tiers).

What it can do on your machine

Read from SKILL.md and the folder at commit e3f4c4d. 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

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • pip
    • bash
    • conda

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com
    • download.pytorch.org

    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

Build Vllm Onednn Zendnn loads about 5.2k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 2,323 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~5.2k

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 2,323 words (~5,169 tokens).

“Take a user from clean repos to a working, verified vLLM CPU build using the direct oneDNN → vLLM CPU integration path (no zentorch). This skill encodes the flow as a linear, stop-on-failure orchestration.”

— opening of SKILL.md by amd, Custom licence
name
build-vllm-onednn-zendnn
version
1.4.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files in .claude/skills/build-vllm-onednn-zendnn of amd/ZenDNN.

  • SKILL.md
  • build-vllm-onednn-zendnn-flow.mmd
  • build_wheel.sh
  • create_env.sh
  • vllm-onednn-zendnn.patch

Open the folder on GitHubat commit e3f4c4d

Compare with similar skills

Build Vllm Onednn Zendnn 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.

Build Vllm Onednn Zendnn compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Build Vllm Onednn Zendnn this skillamd/ZenDNN158—~5.2kAutomated safety check: PassCustom licence
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Aider DelegateamElnagdy/delegate-skills2.3k2 repos~3kAutomated safety check: PassMIT
Hugging Face Local Model Evalshuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
Diffusion Perf Optvllm-project/vllm-omni7.1k—~7.5kAutomated safety check: PassApache-2.0
Ascend Release Manager for vLLMvllm-project/vllm-ascend2.9k—~7.2kAutomated safety check: PassApache-2.0

Similar skills

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Aider Delegate

    amElnagdy/delegate-skills

    Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.

    2.3k GitHub starsUsed in 2 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Model Evals

    huggingface/skills

    Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Diffusion Perf Opt

    vllm-project/vllm-omni

    Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation.

    7.1k GitHub stars~7.5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Ascend Release Manager for vLLM

    vllm-project/vllm-ascend

    Runs the end-to-end vLLM Ascend release process: opens the release checklist and feedback issues, scans for release-blocking bugs and test coverage gaps, and generates release notes and announcements.

    2.9k GitHub stars~7.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Quantization

    vllm-project/vllm-omni

    Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.

    7.1k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from amd/ZenDNN

  • Build Zendnn

    amd/ZenDNN

    Build the standalone ZenDNN native library (zendnnl) from source with the alternate compute backends OFF (no oneDNN, libxsmm, parlooper, fbgemm), keeping AOCL DLP, which is the GEMM backend zendnnl…

    158 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about Build Vllm Onednn Zendnn

What does Build Vllm Onednn Zendnn do?

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch). Build Vllm Onednn Zendnn is an agent skill from amd/ZenDNN. Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

When should I use Build Vllm Onednn Zendnn?

Build Vllm Onednn Zendnn fits situations like: asked to build vLLM CPU against oneDNN/ZenDNN; produce a ZenDNN-enabled vLLM wheel.

How do I install Build Vllm Onednn Zendnn in Claude Code?

Run `npx skills add amd/ZenDNN --skill build-vllm-onednn-zendnn -a claude-code`. Or copy the skill folder (.claude/skills/build-vllm-onednn-zendnn in amd/ZenDNN) into .claude/skills/build-vllm-onednn-zendnn in your project. Claude Code loads it when a task matches its description.

How do I install Build Vllm Onednn Zendnn in Codex?

Run `npx skills add amd/ZenDNN --skill build-vllm-onednn-zendnn -a codex`. Or copy the skill folder (.claude/skills/build-vllm-onednn-zendnn in amd/ZenDNN) into .agents/skills/build-vllm-onednn-zendnn in your project. Codex loads it when a task matches its description.

Can I use Build Vllm Onednn Zendnn 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/ZenDNN --skill build-vllm-onednn-zendnn -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/build-vllm-onednn-zendnn, .gemini/skills/build-vllm-onednn-zendnn, .github/skills/build-vllm-onednn-zendnn and .opencode/skills/build-vllm-onednn-zendnn in your project.

What does Build Vllm Onednn Zendnn need to run?

Going by SKILL.md and its folder, Build Vllm Onednn Zendnn needs a shell for the scripts in its folder and the command-line tools its instructions call (git, pip, bash and conda). Our summary lists: A Bash shell.

Does Build Vllm Onednn Zendnn access the network?

SKILL.md names 2 domains. In commands or code: github.com and download.pytorch.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Build Vllm Onednn Zendnn 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 Build Vllm Onednn Zendnn use?

Build Vllm Onednn Zendnn 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 Build Vllm Onednn Zendnn use?

About 5.2k tokens (SKILL.md is roughly 21k 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 Build Vllm Onednn Zendnn?

Skills that share tags, products or a category with Build Vllm Onednn Zendnn: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Aider Delegate (amElnagdy/delegate-skills, 2.3k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars) and Diffusion Perf Opt (vllm-project/vllm-omni, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Build Vllm Onednn Zendnn?

amd (a GitHub organization) maintains it in amd/ZenDNN, which has 158 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.

Source: amd/ZenDNN on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.