SegFormer

• Original code: https://github.com/huggingface/transformers at c4c4605f9618
• Code licence: Apache-2.0 (permissive); files:
• Weights licence: LicenseRef-NVIDIA-Source-Code-License-NC
• Licence evidence: https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512/blob/489d5cd81a0b59fab9b7ea758d3548ebe99677da/README.md
• Training data: ImageNet-1k (ILSVRC 2012 classification), ADE20K (SceneParsing, 150 classes)
• Kernel libraries: cudnn_hacc, fvm_conv, fvm_extra, fvm_mb, fvm_r3, seg_up
• Variants: segformer-b0-ade20k, segformer-b5-ade20k
• Outputs: logits; label_set: ade20k-150
• Input size: any H x W >= 1, resized or padded inside the model
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): segformer-b0-ade20k 3000x4000 (3.8 GiB peak allocated, 4.0 reserved); segformer-b5-ade20k 3000x4000 (4.0 GiB peak allocated, 4.3 reserved)
• segformer-b0-ade20k 1024x2048, first call: portable + torch.compile 12 s (cold Inductor cache), TensorRT fp16 61 s (ONNX + engine).
• segformer-b0-ade20k original 1024x2048: torch.autocast(fp16) around the forward
• segformer-b5-ade20k original 1024x2048: torch.autocast(fp16) around the forward
• segformer-b0-ade20k load / first call: original 4.83 s / 2.232 s (512x512), portable 2.55 s / 0.082 s, kernels 2.92 s / 0.009 s
• segformer-b5-ade20k load / first call: original 1.24 s / 0.501 s (512x512), portable 3.09 s / 0.077 s, kernels 3.43 s / 0.032 s
• Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5 (tools/speed_check.py), synthetic CUDA input (bench_inputs); peak = max over the first call and the timed calls

Measured

Each image at its own size, argmax of the logits. Original = the original code named under Details, same checkpoint and protocol.

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.

Parity

CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.1 (absolute error of the output logits).