Model card synced with fastforks 7204e33f

README.md

@@ -60,6 +60,12 @@ Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `monster-mix-all` 1988x2880 (6
 | --- | --- | --- | --- | --- | --- | --- |
 | `monster-mix-all` | 5.85 (375x1242) | 4.83 | 0.95† | 1.26 (375x1242) | 1.59† | 0.67† |
 
+### 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) |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| `monster-sceneflow` | 994x1482 | 1585.15 | 1096.3 | 102.6 | fails: ONNX export: conversion failed | – | 667.63 | 2336 / 2494 | 2081 / 2272 | – |
+
 ### Fixed-size speed and peak memory, all models
 
 | model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
@@ -69,6 +75,12 @@ Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `monster-mix-all` 1988x2880 (6
 | `monster-sceneflow` | portable | 284.1 ms / 1089 / 1184 | 894.5 ms / 1732 / 2154 | 2290.9 ms (n=3) / 2935 / 3668 | OOM |
 | `monster-sceneflow` | kernels | 127.1 ms / 1112 / 1250 | 379.4 ms / 1752 / 2288 | 956.9 ms / 2939 / 3460 | OOM |
 
+### Apple silicon (MPS)
+
+| model | `portable` | `kernels` | speed-up |
+| --- | --- | --- | --- |
+| `monster-sceneflow` | 3344 ms / 3491 MiB (float16) | 2756 ms / 4093 MiB | 1.21x |
+
 Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
 
 - `monster-sceneflow`: same network and settings as `monster-mix-all`, measured once (rows not repeated).
@@ -86,7 +98,8 @@ Every variant is checked against golden outputs of the original code at its pinn
 ```python
 from fastforks import stereo
 
-model = stereo.load("monster-mix-all")  # portable PyTorch on the GPU if there is one, else the CPU
+# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
+model = stereo.load("monster-mix-all")  # mode="auto": the preferred backend from recorded measurements
 result = model("left.png", "right.png")
 result.disparity  # [H, W] float32 tensor, input resolution
 result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
@@ -97,3 +110,5 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
 ## Kernels backend
 
 `stereo.load("monster-mix-all", mode="kernels")` runs our CUDA kernels (`igev`, `cutlass_conv`, `cudnn_hacc`, `fastbb`). 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) -->