All skills
trtllm-visualgen-bench
Benchmarks a TensorRT-LLM VisualGen model end to end, including bringing up the trtllm-serve server it needs.
- Part of NVIDIA/TensorRT-LLM
- Machine Learning · Vision models
More Vision models skills
See all- deepstream-dev2.5kBuilds DeepStream video analytics pipelines in Python with inference, tracking and message broker output.
- deepstream-import-vision-model2.3kBrings an object-detection model from HuggingFace or NGC into a DeepStream pipeline with engine build and benchmark.
- h3-image-prompt-writing174Writes MiniMax-H3-Image prompts for posters, infographics, product shots, characters and scenes, and can render them.
- segment-anything-model26Segments objects in images from points, boxes or masks without extra training.
Also in this pack
- perf-nsight-systems41Runs Nsight Systems profiling and reads timeline reports to find GPU idle time and NCCL overlap issues.
- perf-nsight-compute-analysis37Interprets Nsight Compute reports, classifying bottlenecks by SOL, roofline, occupancy, memory and warp stalls.
- kernel-triton-writing27Writes and verifies OpenAI Triton kernels such as fused elementwise, reductions, tiled GEMM and attention.
- perf-optimization18Routes performance work to the right specialist and applies optimizations or kernels in a safe order.