creator profile · 234 approved skills · page 16 of 24
nvidia publishes 234 approved skills on explainx.ai. This page loads 10 skills at a time. Current page is led by jetson-speculative-decoding.
total skills
234
showing 10 on this page
page installs
0
0 this week
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, metric types, or plugin-owned Evaluator skills.
>-
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL…
