nvidia/dl4agx

How nvidia/dl4agx works

DL4AGX is a collection of autonomous-vehicle model designs, TensorRT deployment solutions, and inference samples for NVIDIA DRIVE—not a single application. Its user-facing workflow is generally to prepare or export a model, deploy it with a platform-specific inference solution, and inspect or visualize results. The README also names quantization, sparsity, plugin, and LLM deployment capabilities, which are preserved as separate branches. Most source excerpts cover selected inference apps; dashed, uncited links mark broader workflows that the available evidence does not verify in detail.

Main entry points: uniad.hpp UniAD Kernel · export_onnx.py ONNX Export · inference.py TensorRT Engine · dcnv4-trt DCNv4 TensorRT

Components 28

Model Designs

DEST Models Models/DEST/networks/DESTNet.py
ReduceFormer Models/ReduceFormer/reduceformer/backbone.py

AV Deployment

DCNv4 TensorRT AV-Solutions/dcnv4-trt
Far3D TensorRT AV-Solutions/far3d-trt/inference_app/lib/far3d.cpp
MTMI TensorRT AV-Solutions/mtmi/inference_app/main.cpp
PETR TensorRT AV-Solutions/petr-trt/app/petrv2.cpp
StreamPETR TensorRT AV-Solutions/streampetr-trt/inference_app/main.cpp
UniAD TensorRT AV-Solutions/uniad-trt/inference_app/enqueueV2/src/main.cpp
VAD TensorRT AV-Solutions/vad-trt/app/main.cpp
BEVFormer INT8 AV-Solutions/bevformer-int8-eq
Sparsity INT8 AV-Solutions/SparsityINT8
TensorRT-LLM AV-Solutions/llms-trtllm/json_modifier.py
Diffusion Planner AV-Solutions/diffusion_planner-trt

Inference Apps

Far3D Runtime AV-Solutions/far3d-trt/inference_app/lib/far3d.cpp
Tensor Utilities AV-Solutions/far3d-trt/inference_app/include/tensor.hpp
UniAD Kernel AV-Solutions/uniad-trt/inference_app/enqueueV2/include/uniad.hpp
Input Preparation AV-Solutions/uniad-trt/inference_app/enqueueV2/include/pre_process.hpp
Output Processing AV-Solutions/uniad-trt/inference_app/enqueueV2/include/post_process.hpp
AV Visualization AV-Solutions/vad-trt/app/lib/visualize.hpp
cuDLA Context AV-Solutions/mtmi/inference_app/src/cudla_context.cpp

Model Preparation

ONNX Export AV-Solutions/far3d-trt/tools/export_onnx.py
ONNX Quantization AV-Solutions/far3d-trt/tools/quantize_onnx.py
Calibration Data AV-Solutions/uniad-trt/tools/prepare_calib_data.py
TensorRT Engine AV-Solutions/vad-trt/export_eval/bev_deploy/trt/inference.py

Deployment Extensions

TensorRT Plugins AV-Solutions/vad-trt/plugins
PTX Plugin Guidance AV-Solutions/triton2cubin-plugin-guidance
ONNX Export Guidance AV-Solutions/onnx-export-guidance

Other components

AV Engineer

Connections 28

AV Engineer → DEST Models: selects model
AV Engineer → ReduceFormer: selects model
AV Engineer → ONNX Export: prepares model
ONNX Export → TensorRT Engine: exports ONNX
ONNX Quantization → TensorRT Engine: quantizes model
Calibration Data → TensorRT Engine: supplies calibration
AV Engineer → DCNv4 TensorRT: deploys model
AV Engineer → Far3D TensorRT: runs inference
AV Engineer → MTMI TensorRT: runs inference
AV Engineer → PETR TensorRT: runs inference
AV Engineer → StreamPETR TensorRT: runs inference
AV Engineer → UniAD TensorRT: runs inference
AV Engineer → VAD TensorRT: runs inference
AV Engineer → BEVFormer INT8: quantizes model
AV Engineer → Sparsity INT8: trains model
AV Engineer → TensorRT-LLM: deploys LLM
AV Engineer → Diffusion Planner: deploys planner
Far3D TensorRT → Far3D Runtime: runs inference AV-Solutions/far3d-trt/inference_app/lib/far3d.cpp
Far3D Runtime → Tensor Utilities: uses tensors
AV Engineer → UniAD Kernel: runs inference
UniAD Kernel → Input Preparation: prepares inputs AV-Solutions/uniad-trt/inference_app/enqueueV2/include/pre_process.hpp
UniAD Kernel → Output Processing: processes outputs AV-Solutions/uniad-trt/inference_app/enqueueV2/include/post_process.hpp
AV Engineer → AV Visualization: views results
MTMI TensorRT → cuDLA Context: uses context AV-Solutions/mtmi/inference_app/main.cpp
VAD TensorRT → AV Visualization: renders results AV-Solutions/vad-trt/app/main.cpp
DCNv4 TensorRT → TensorRT Plugins: uses plugins
TensorRT Plugins → PTX Plugin Guidance: integration guidance
ONNX Export → ONNX Export Guidance: export guidance

More Shell diagrams: ading2210/shimboot · pwnerblu/surrealra1n · opf/openproject-docker-compose · allienx/libdvdcss-dll · armbian/os

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·