Self-hosted alternatives to jetson-inference-mem-tune
No self-hosted apps like jetson-inference-mem-tune yet.
About jetson-inference-mem-tune
J
jetson-inference-mem-tune
Pick the serving stack and per-runtime memory flags
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.
- Price
- Free
- Made by
- nvidia
- Category
- AI Skills
- Website
- github.com/nvidia/skills/jetson-inference-mem-tune