Model card synced with fastforks 7204e33f

README.md

@@ -60,6 +60,12 @@ Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `vggt-1b` 3000x4000 (8.0 GiB p
 | --- | --- | --- | --- | --- | --- | --- |
 | `vggt-1b` | 19.37 (336x518) | 4.98 (336x518) | 5.99† (336x518) | 1.29 (336x518) | 0.69 (336x518) | 0.46 (336x518) |
 
+### 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) |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| `vggt-1b` | 336x518 | 651.18 | fails: Inductor: inference tensors | – | fails: TensorRT: antialiased resize not supported | – | 458.37 | 3691 / 4674 | – | – |
+
 ### Fixed-size speed and peak memory, all models
 
 | model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
@@ -75,17 +81,17 @@ Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastfo
 
 ### 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 px and p99 <= 0.25 px.
+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 <= 0.25 (absolute error of the output `depth`).
 
 ## Usage
 
 ```python
 from fastforks import multiview
 
-model = multiview.load("vggt-1b")  # portable PyTorch on the GPU if there is one, else the CPU
-result = model(["view0.jpg", "view1.jpg", "view2.jpg"])  # the views of one scene
+# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
+model = multiview.load("vggt-1b")  # mode="auto": the preferred backend from recorded measurements
+result = model(["view0.jpg", "view1.jpg", "view2.jpg"])  # the views of one scene, no cameras needed
 result.depth  # [V, H, W] float32 tensor; result.kind says what the maps mean
-# calibrated MVS: model(views, intrinsics=K, cam_to_world=c2w), K [N, 3, 3], c2w [N, 4, 4]
 result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
 ```
 
@@ -94,3 +100,5 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
 ## Kernels backend
 
 `multiview.load("vggt-1b", mode="kernels")` runs our CUDA kernels (`fastbb`, `cudnn_hacc`). 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) -->