---
library_name: "fastforks"
pipeline_tag: "image-classification"
license: "apache-2.0"
tags:
- "classification"
- "image-classification"
- "cuda"
- "pytorch"
- "fastforks"
---
# Vision Transformer (fastforks)

Vision Transformer (Dosovitskiy et al. 2020): 16x16 patches, pre-norm transformer encoder, class token.

This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: <https://github.com/kleinicke/fastforks>. Kernels for the `kernels` backend: <https://huggingface.co/fastforks/kernels>. Original code: <https://github.com/huggingface/pytorch-image-models> at `0df212b369a5`.

Author weight repos: <https://huggingface.co/timm/vit_base_patch16_224.augreg2_in21k_ft_in1k>.

Task: classification. Tier: stable. Outputs: `logits`. Backends: `portable`, `kernels`.

Input: one RGB image. Output: ImageNet-1k class logits.

## Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in [`card.toml`](https://github.com/kleinicke/fastforks/blob/main/src/fastforks/classification/models/vit/card.toml).

| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
| `vit_base_patch16_224.augreg2_in21k_ft_in1k@1` | [vit_base_patch16_224.augreg2_in21k_ft_in1k.safetensors](https://huggingface.co/timm/vit_base_patch16_224.augreg2_in21k_ft_in1k/resolve/063c6c38a5d8510b2e57df480445e94b231dad2c/model.safetensors) | `32aa17d6e17b` | Apache-2.0 | yes |

## Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Files: .

Training data: ImageNet-21k / ImageNet-22k (full ImageNet, fall 2011 release), ImageNet-1k (ILSVRC 2012 classification).

Licence evidence: <https://huggingface.co/timm/vit_base_patch16_224.augreg2_in21k_ft_in1k/blob/063c6c38a5d8510b2e57df480445e94b231dad2c/README.md>

## Input size

fixed 224x224: the input is resized (short side 248) and centre-cropped to it
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `vit_base_patch16_224.augreg2_in21k_ft_in1k` 224x224 (0.2 GiB peak allocated, 0.3 reserved)

## Speed and memory

### Classification, synthetic, 224x224

| model | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `vit_base_patch16_224.augreg2_in21k_ft_in1k` | 6.33 | 5.48 | 3.02 | 1.647 | 3.3x | 1.8x | 531 / 548 | 205 / 390 | 300 / 370 |

### Startup and first call

| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- |
| `vit_base_patch16_224.augreg2_in21k_ft_in1k` | 2.49 | 0.73 | 2.05 | 0.28 | 0.00 | 0.07 |

### torch.compile and TensorRT

| model | input | portable ms | compile ms | compile s (cold) | TensorRT fp16 ms | ONNX + build s | kernels ms | peak MiB (alloc / reserved): portable | compile | TensorRT (device) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `vit_base_patch16_224.augreg2_in21k_ft_in1k` | 224x224 | 3.02 | 2.1 | 7.3 | 1.1 | 29 | 1.647 | 205 / 390 | 238 / 266 | 196 |

### Fixed-size speed and peak memory, all models

| model | mode | 224x224 |
| --- | --- | --- |
| `vit_base_patch16_224.augreg2_in21k_ft_in1k` | portable | 2.9 ms / 214 / 338 |
| `vit_base_patch16_224.augreg2_in21k_ft_in1k` | kernels | 1.8 ms / 316 / 418 |

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastforks/blob/main/docs/benchmarks.md) (RTX 5060 Ti 16 GB, sm_120). Original = the authors' code at the precision of portable (fp16, or `(fp32)` where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.

## Accuracy

### Parity with the original code

Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.08 (absolute error of the output `logits`).

## Usage

```python
from fastforks import classification

model = classification.load("vit_base_patch16_224.augreg2_in21k_ft_in1k")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg")
result.top(5)  # top-5 classes
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
```

Install with `pip install fastforks` (see <https://github.com/kleinicke/fastforks>). Other variants: `vit_base_patch16_224.augreg2_in21k_ft_in1k`.

## Kernels backend

`classification.load("vit_base_patch16_224.augreg2_in21k_ft_in1k", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`, `fvm_conv`, `fvm_extra`, `fvm_mb`, `fvm_r3`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.

<!-- staged from fastforks 7204e33f (2026-11-05) -->