jetson-speculative-decoding SKILL.md skillA
jetson-speculative-decoding from nvidia/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia/skills/jetson-speculative-decoding@v0.0.1Pins v0.0.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia/skills
- Path
skills/jetson-speculative-decoding/SKILL.md- Versions recorded
- 1
- Latest version
- v0.0.1, committed Jun 22, 2026
- Size
- 4,832 bytes
- Repository stars
- 3,871
- License
- Apache-2.0
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Jetson Speculative Decoding (vLLM) Speculative decoding lets a small "draft" model propose tokens that the target model verifies in a single forward pass, reducing per-token latency. On Jetson, the win/loss is **dominated by VRAM headroom**, not by the draft quality. This skill encodes the parts an LLM won't already know. ## Purpose Tune an existing Jetson vLLM deployment for faster token generation by appending the right `--speculative-config` and validating whether it improves single-stream decode speed. ## When to use - TPOT/ITL is the bottleneck (TTFT is fine, output is just slow). - Workload is single-stream or low-concurrency (≤2). Speculation usually loses at high concurrency. - Jetson family is **Thor or AGX Orin**. Do **not** suggest EAGLE-3 on Orin Nano/NX — there is rarely enough VRAM headroom to host both target and draft, and you'll OOM at startup. ## When NOT to use - High-concurrency serving (≥8): batched decode usually beats speculation; the draft model just steals VRAM. - Models without a published EAGLE-3 head — do not train one ad-hoc as a "fix". …
Read the whole file at its exact version.
How to install
mdr add nvidia/skills/jetson-speculative-decoding@sha256:a94e228320c83370The line at the top of this page pins the label v0.0.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_76c7wktj5zzddbm3)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jun 22, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4832 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nvidia/skills · 3,871 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_76c7wktj5zzddbm3 GET https://markdownregistry.com/api/v1/resolve?ref=nvidia/skills/jetson-speculative-decoding GET https://markdownregistry.com/api/v1/blob/a94e228320c83370322f427d3245abe0c03f3963e10db7226d8beac40f5cc0fe
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.