All skills
perf-optimization-casebook
Suggests proven TensorRT-LLM optimizations for a given bottleneck, config or hardware, with risks and rollback.
- Part of NVIDIA/TensorRT-LLM
- Machine Learning · Model serving
More Model serving skills
See all- serving-llms-vllm66Serves large language models at high throughput with an OpenAI-compatible API and quantization.
- tensorrt-llm21Runs high-throughput language model inference on NVIDIA GPUs.
- inference-optimisation16Measures and tunes local LLM serving speed, testing changes one at a time and keeping a record of results.
- vllm2Deploys and serves language models with vLLM behind an OpenAI-compatible endpoint with tool calling.
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.