Search
CUDA · NVIDIA/skills
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2dcv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT… | NVIDIA/ | 3.6k | — | ~4.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 50 | Build Holoscan SDK from source via the in-tree ./run script. | NVIDIA/ | 3.6k | — | ~1.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 51 | Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer. | NVIDIA/ | 3.6k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 52 | Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules. | NVIDIA/ | 3.6k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 53 | Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP. | NVIDIA/ | 3.6k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 54 | Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. | NVIDIA/ | 3.6k | — | ~973 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 55 | Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM… | NVIDIA/ | 3.6k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 56 | MoE expert-parallel communication overlap in Megatron Bridge. | NVIDIA/ | 3.6k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 57 | Representative, point-in-time MoE training playbooks by hardware and model family. | NVIDIA/ | 3.6k | — | ~2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 58 | Long-context MoE training guidance for Megatron Bridge. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.6k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 59 | Evidence-gated workflow for MoE performance optimization in Megatron Bridge. | NVIDIA/ | 3.6k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 60 | Practical guidance for training MoE VLMs in Megatron Bridge. | NVIDIA/ | 3.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 61 | Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. | NVIDIA/ | 3.6k | — | ~924 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 62 | One-time session setup and orchestration map for the TAO skill bank. | NVIDIA/ | 3.6k | — | ~1.8k | Automated safety check: Warn | Apache-2.0 | 2 days ago |
| 63 | The Docker execution platform for TAO jobs — a local daemon or a remote GPU box via DOCKERHOST=ssh://user@host. | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Warn | Apache-2.0 | 2 days ago |
