Model card synced with fastforks 7204e33f

README.md

@@ -20,7 +20,7 @@ This repo is the model card only: it holds no weights. fastforks downloads the a
 
 Task: depth. Tier: experimental. Outputs: `inverse_depth`. Backends: `portable`, `kernels`.
 
-Input: one RGB image. Output: a depth or inverse-depth map (metric for the models marked `metric`).
+Input: one RGB image. Output: a depth or inverse-depth map. `kind` (a card field, `result.kind`) says what the numbers mean: `metric` = metres; `scale_invariant`, `affine_invariant` and `affine_invariant_inverse` are relative (unknown scale or shift, not metres). Metric models that use the focal length take `model(image, intrinsics=K)` (K `[3, 3]`, pixels of the input): `metric3d-vit-large` and `da3metric-large` need it for correct metres (`da3metric-large`: metres = output x focal / 300; without `intrinsics=` a 300 px focal length is assumed, wrong for a real camera). `unidepth-v2-vitl14`, `unik3d-vitl`, `depth-pro` and MoGe estimate the camera themselves (given `intrinsics=` replace `fx`); `zoedepth-nk` and the relative models (`da3mono-large` too) take none.
 
 ## Variants
 
@@ -59,6 +59,12 @@ Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `midas-dpt-beit-large-512` 300
 | --- | --- | --- | --- | --- | --- | --- |
 | `midas-dpt-beit-large-512` | 5.16 | 2.49 | 0.28† | 1.14 | 0.09 | 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) |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| `midas-dpt-beit-large-512` | 994x1482 | 78.79 | fails: Dynamo: inference_mode in model code | – | 52.2 | 54 | 63.89 | 992 / 1418 | – | 800 |
+
 ### Fixed-size speed and peak memory, all models
 
 | model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
@@ -89,14 +95,14 @@ Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, 2026-10-27.
 
 ### Parity with the original code
 
-Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.02 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.5 % and p99 <= 2 % 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| <= 0.02 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.5 % and p99 <= 2 % of the reference's median |value| (absolute error of the output `inverse_depth`).
 
 ## Usage
 
 ```python
 from fastforks import depth
 
-model = depth.load("midas-dpt-beit-large-512")  # portable PyTorch on the GPU if there is one, else the CPU
+model = depth.load("midas-dpt-beit-large-512")  # mode="auto": the preferred backend from recorded measurements
 result = model("room.jpg")
 result.inverse_depth  # [H, W] float32 tensor; result.kind says what the maps mean
 # models that take a camera: model("room.jpg", intrinsics=K), K [3, 3] in pixels
@@ -108,3 +114,5 @@ Install with `pip install fastforks` (see <https://github.com/kleinicke/fastfork
 ## Kernels backend
 
 `depth.load("midas-dpt-beit-large-512", mode="kernels")` runs our CUDA kernels (`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) -->