Model card synced with fastforks 7204e33f

README.md

@@ -62,6 +62,12 @@ Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `patchmatchnet` 1988x2880 (7.9
 | --- | --- | --- | --- | --- | --- | --- |
 | `patchmatchnet` | 0.04 (1536x1024) | 0.06 (1536x1024) | 0.05† (1536x1024) | 0.92 (1536x1024) | 0.25 (1536x1024) | 0.04 (1536x1024) |
 
+### 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) |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| `patchmatchnet` | 1536x1024 | 201.66 | 175.0 | 29.4 | 28.2 | 54 | 29.57 | 1806 / 2096 | 1798 / 1888 | 790 |
+
 ### Fixed-size speed and peak memory, all models
 
 | model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
@@ -77,17 +83,16 @@ 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| <= 0.5 % and p99 <= 3 % of the reference's median |value|.
+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| <= 0.5 % and p99 <= 3 % of the reference's median |value| (absolute error of the output `depth`).
 
 ## Usage
 
 ```python
 from fastforks import multiview
 
-model = multiview.load("patchmatchnet")  # 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
-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]
+model = multiview.load("patchmatchnet")  # mode="auto": the preferred backend from recorded measurements
+result = model(["ref.jpg", "src1.jpg", "src2.jpg"], intrinsics=K, cam_to_world=c2w, depth_range=(0.5, 5.0))
+result.depth  # [1, H, W] float32 tensor; views[0] = reference, K [N, 3, 3] pixels, c2w [N, 4, 4] OpenCV
 result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
 ```
 
@@ -96,3 +101,5 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
 ## Kernels backend
 
 `multiview.load("patchmatchnet", mode="kernels")` runs our CUDA kernels (`patchmatchnet`). 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) -->