torch-xpu-bench
intel/gpu-ai-skillsBenchmark a Hugging Face model on an Intel GPU through pure PyTorch + Transformers, **single-process, no HTTP server**. Measures generate() throughput in…
Scores out of 100 · grade A
2026-08-22Works
40% of the score100/100
- Loads cleanly: valid frontmatter, required fields present, no dangling references.
Maintained
25% of the score100/100
- no commits in the last 12 weeks
- repo is less than two weeks old
Adopted
20% of the score8/100
- 3 stars on the source repo.
Documented
15% of the score100/100
- 932 words with worked examples.
- Ships 2 bundled files.
Install
npx skills add intel/gpu-ai-skills/torch-xpu-benchWhat it says it does
Benchmark a Hugging Face model on an Intel GPU through pure PyTorch + Transformers, **single-process, no HTTP server**. Measures generate() throughput in tokens/sec, time-to-first-token, decode-step latency, and peak XPU memory. Also covers diffusion and encoder-only models via `references/non-llm-snippets.md`. Use after **model-can-it-fit** to validate predicted memory against `torch.xpu.max_memory_allocated()`.
Also in intel/gpu-ai-skills
| Artifact | Score | What the check found | Type | Reach | Last commit |
|---|---|---|---|---|---|
| vllm-xpu-runintel/gpu-ai-skills | clean | Skill | 3 stars | today | |
| xpu-portintel/gpu-ai-skills | clean | Skill | 3 stars | today | |
| model-can-it-fitintel/gpu-ai-skills | clean | Skill | 3 stars | today | |
| model-config-recommendintel/gpu-ai-skills | clean | Skill | 3 stars | today | |
| sglang-xpu-runintel/gpu-ai-skills | clean | Skill | 3 stars | today | |
| vllm-xpu-benchintel/gpu-ai-skills | clean | Skill | 3 stars | today |
Other backend & apis skills
Browse all| Artifact | Score | What the check found | Category | Reach | Last commit |
|---|---|---|---|---|---|
| find-skillsvercel-labs/skills | clean | Backend & APIs | 3,055,082 installs | 3 days ago | |
| write-api-referencevercel/next.js | clean | Backend & APIs | 142k stars | today | |
| fastapifastapi/fastapi | clean | Backend & APIs | 8,017 installs | 2 days ago | |
| paperclippaperclipai/paperclip | clean | Backend & APIs | 3,217 installs | today | |
| onchain-pay-open-apiccxt/ccxt | clean | Backend & APIs | 44k stars | today | |
| namecheapgithub/awesome-copilot | clean | Backend & APIs | 38k stars | today |
Put this measurement in your README
A badge carrying how many listings this index holds from the repository and how many pass every static structural check. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://skillworks.kynth.studio/?q=intel%2Fgpu-ai-skills)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.
