AI model or service
NVIDIA AI Platform agent skills, page 10
NVIDIA AI Platform skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 433 | Verl 单异步 DAPO 训练配置生成器。触发场景：(1) 启动单异步 DAPO 训练 (2) 生成训练脚本 (3) 配置特性参数 (4) 训练前检查。特性策略：用户未指定时默认开启性能特性（flashattn/dynamicbatch/removepadding/gradientcheckpointing），显存特性（offload/recompute）默认关闭。OOM… | ascend-ai-coding/ | 174 | — | ~1.2k | Automated safety check: Pass | No licence | today |
| 434 | MindSpeed-MM multimodal model suite environment setup guide for Huawei Ascend NPU. | ascend-ai-coding/ | 174 | — | ~3.1k | Automated safety check: Pass | No licence | today |
| 435 | 435.Mindspeed Mm Vlm Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM. | ascend-ai-coding/ | 174 | — | ~5.2k | Automated safety check: Pass | No licence | today |
| 436 | 436.Verl Quickstart Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow). | ascend-ai-coding/ | 174 | — | ~592 | Automated safety check: Pass | No licence | today |
| 437 | 437.Parakeet Stt Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). | sundial-org/ | 663 | — | ~771 | Automated safety check: Pass | No licence | 7 mo ago |
| 438 | 438.Cublas Cudnn Expert integration with NVIDIA GPU-accelerated math libraries. | majiayu000/ | 666 | 1 repo | ~2.4k | Automated safety check: Notes | MIT | today |
| 439 | Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. | majiayu000/ | 666 | 1 repo | ~2.1k | Automated safety check: Pass | MIT | today |
| 440 | NVIDIA Collective Communications Library integration for multi-GPU operations. | majiayu000/ | 666 | 1 repo | ~1.9k | Automated safety check: Notes | MIT | today |
| 441 | NVIDIA TensorRT model optimization and deployment. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 1 repo | ~2.4k | Automated safety check: Notes | MIT | today |
| 442 | Proteina-Complexa flow-based protein backbone generation with fold-conditioned sampling guidance. | BioTender-max/ | 197 | — | ~1.4k | Automated safety check: Notes | MIT | 3 mo ago |
| 443 | 443.Cuda CUDA C/C++ skill for NVIDIA GPU kernel programming. An agent skill from mohitmishra786/low-level-dev-skills. | mohitmishra786/ | 253 | — | ~1.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 444 | 444.Cuda Debugging CUDA debugging skill for GPU program correctness. An agent skill from mohitmishra786/low-level-dev-skills. | mohitmishra786/ | 253 | — | ~1.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 445 | 445.Cuda Profiling CUDA profiling skill for NVIDIA GPU performance analysis. An agent skill from mohitmishra786/low-level-dev-skills. | mohitmishra786/ | 253 | — | ~1.6k | Automated safety check: Notes | MIT | 3 mo ago |
| 446 | 446.GPU Memory Model GPU memory model skill for SIMT execution and memory hierarchy. | mohitmishra786/ | 253 | — | ~1.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 447 | Build machine vision inspection systems with MATLAB Visual Inspection Toolbox. | matlab/ | 1.1k | — | ~3.1k | Automated safety check: Pass | Unknown | 7 days ago |
| 448 | Implement comprehensive safety guardrails for LLM applications including content moderation (OpenAI Moderation API), jailbreak prevention, prompt injection defense, PII detection, topic guardrails… | omer-metin/ | 162 | — | ~544 | Automated safety check: Pass | Apache-2.0 | 8 mo ago |
| 449 | Elite Computer Vision Engineer skill with expertise in deep learning for images and video (CNNs, Transformers), object detection (YOLO, DETR), segmentation, OCR, and production CV deployment… | theneoai/ | 183 | — | ~2.2k | Automated safety check: Pass | MIT | 4 mo ago |
| 450 | LLM serving expert: vLLM, TensorRT-LLM, Triton Inference Server, quantization (INT8/FP8/GPTQ/AWQ), continuous batching, PagedAttention, KV cache management. | theneoai/ | 183 | — | ~3.4k | Automated safety check: Pass | MIT | 4 mo ago |
| 451 | Expert robot perception engineer specializing in 3D point cloud processing, multi-modal sensor fusion (camera+LiDAR+IMU), real-time SLAM, and edge-optimized deep learning inference via TensorRT/ONNX… | theneoai/ | 183 | — | ~1.5k | Automated safety check: Pass | MIT | 4 mo ago |
| 452 | Interpret NVIDIA Nsight Compute evidence for a CUDA kernel task. | uw-syfi/ | 103 | — | ~298 | Automated safety check: Pass | MIT | yesterday |
