Verified record · from the answer index
jetson-inference-mem-tune
skilltested · static-verifiedscore 50/100signed passport ✓1,187 uses
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.
Declared tools (1)
jetson-inference-mem-tune
skill:nvidia/skills/jetson-inference-mem-tune · published by nvidia · source repository