Skip to content
store
J

jetson-inference-mem-tune

Pick the serving stack and per-runtime memory flags

by nvidiaFree

Launch
#4854in AI Skills
0In stores

Description

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetso…

Ratings & Reviews

No ratings yet

Be the first to rate jetson-inference-mem-tune.

People also visit

F

frontend-design

Instructs Claude to avoid "AI slop" or generic aesthetics

AI Skills
Launch
A

artifacts-builder

Suite of tools for creating elaborate

AI Skills
Launch
C

canvas-design

Design beautiful visual art in .png and .pdf formats using design philosophies

AI Skills
Launch
M

mcp-builder

Guide for creating high-quality MCP servers to integrate external APIs

AI Skills
Launch
P

pdf

Extract text, tables, metadata, merge & annotate PDFs

AI Skills
Launch
W

webapp-testing

Test local web applications using Playwright for UI verification and debugging

AI Skills
Launch
See all jetson-inference-mem-tune alternatives

jetson-inference-mem-tune FAQ

What is jetson-inference-mem-tune?

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

Is jetson-inference-mem-tune free?

Yes. jetson-inference-mem-tune is free to use.

Do I need to download jetson-inference-mem-tune?

No. jetson-inference-mem-tune runs in your browser at skills.sh, so there's nothing to install.

Who makes jetson-inference-mem-tune?

jetson-inference-mem-tune is made by nvidia.

What are the best jetson-inference-mem-tune alternatives?

Popular alternatives to jetson-inference-mem-tune include frontend-design, artifacts-builder and canvas-design. See all jetson-inference-mem-tune alternatives

Developer Stuff

Badges