Individual skill
jetson-speculative-decoding
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
skills/jetson-speculative-decoding/SKILL.md
Source commit 25340619336e89bcc40365c28bfe9e790430468e
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 3,888
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- coding-agents Repository topic
- cuda Repository topic
- developer-tools Repository topic
- llm Repository topic
- omniverse Repository topic
- jetson Declared skill tag
- llm Declared skill tag
- speculative-decoding Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
BENCHMARK.mddoc · 3,357 bytesSKILL.mdcore · 4,832 bytesevals/evals.jsonasset · 6,522 bytesskill-card.mddoc · 3,675 bytesskill.oms.sigasset · 4,605 bytes
Read excerpt
# 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.
