Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/MIUAV/vibe-coding-ros2 --skill tensorrtThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| name | tensorrt |
| description | TensorRT推理优化 - 模型转换 引擎构建 INT8量化 |
| argument-hint | TensorRT OR 模型优化 OR INT8量化 OR 引擎生成 |
| user-invocable | true |
NVIDIA推理优化引擎
ONNX/PyTorch -> TensorRT -> Engine -> Inference
import tensorrt as trt
logger = trt.Logger(trt.Logger.WARNING)
builder = trt.Builder(logger)
network = builder.create_network(1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
config = builder.create_builder_config()
parser = trt.OnnxParser(network, logger)
# 解析ONNX
with open('model.onnx', 'rb') as f:
parser.parse(f.read())
# 构建引擎
engine = builder.build_serialized_network(network, config)
# 推理
runtime = trv.Runtime(logger)
engine = runtime.deserialize_cuda_engine(engine)
context = engine.create_execution_context()
context.execute_v2(bindings)