sam / README.md

fastforks 0.1.0

87c020e 2 days ago

6.67 kB

---
library_name: "fastforks"
pipeline_tag: "mask-generation"
license: "apache-2.0"
tags:
- "promptable_segmentation"
- "segment-anything"
- "promptable-segmentation"
- "cuda"
- "pytorch"
- "fastforks"
---
# Segment Anything (SAM) (fastforks)

Segment Anything (Kirillov et al. 2023): promptable segmentation with a ViT image encoder (windowed + global attention, relative positions) and a light prompt encoder / mask decoder; masks from points, boxes and mask logits. The portable `module()` is the image encoder only.

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/facebookresearch/segment-anything> at `dca509f`.

Task: promptable_segmentation. Tier: stable. Outputs: `pred_masks`, `iou_scores`. Backends: `portable`, `kernels`.
Input: one image plus a point, box or text prompt. Output: masks with quality scores.
## 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/promptable_segmentation/models/sam/card.toml).
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
| `sam-vit-b@1` | [sam_vit_b_01ec64.pth](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth) | `ec2df6273261` | Apache-2.0 | yes |
| `sam-vit-h@1` | [sam_vit_h_4b8939.pth](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth) | `a7bf3b02f3eb` | Apache-2.0 | yes |
| `sam-vit-l@1` | [sam_vit_l_0b3195.pth](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth) | `3adcc4315b64` | 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: `LICENSE`.
Training data: SA-1B (11M licensed images, 1.1B automatically generated masks) per the paper; the dataset itself is under the SA-1B research licence.
Licence evidence: https://github.com/facebookresearch/segment-anything/blob/main/README.md (License section: model checkpoints and code under Apache 2.0)
## Input size
any H x W >= 1, resized inside to the fixed encoder input 1024x1024 (the default export size)
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `sam-vit-b` 1080x1920 (0.4 GiB peak allocated, 0.5 reserved); `sam-vit-h` 1080x1920 (1.5 GiB peak allocated, 1.9 reserved); `sam-vit-l` 1080x1920 (0.8 GiB peak allocated, 1.0 reserved)
## Speed and memory
### Promptable segmentation, synthetic, 1024x1024
| model | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `sam-vit-b` | 173 | – | 48.3 | 37.0 | – | 1.3x | – | 378 / 420 | 377 / 420 |
| `sam-vit-h` | 742 | – | 214 | 143 | – | 1.5x | – | 1484 / 2524 | 1480 / 1524 |
| `sam-vit-l` | 414 | – | 116 | 81.5 | – | 1.4x | – | 833 / 1262 | 831 / 862 |
### Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- |
| `sam-vit-b` | 0.76 | 0.46 | 0.17† | 0.27 | 0.05† | 0.04† |
| `sam-vit-h` | 3.53 | 2.45 | 0.89† | 0.73 | 0.21† | 0.14† |
| `sam-vit-l` | 1.46 | 1.21 | 0.43† | 0.42 | 0.12† | 0.08† |
### 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) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `sam-vit-b` | 1024x1024 | 48.3 | 40.9 | 14.5 | 27.3 | 36 | 37.0 | 378 / 420 | 362 / 400 | 322 |
### Fixed-size speed and peak memory, all models
| model | mode | 480x640 | 720x1280 | 1080x1920 | 12 MP 3000x4000 |
| --- | --- | --- | --- | --- | --- |
| `sam-vit-b` | portable | 48.6 ms / 367 / 482 | 48.6 ms / 374 / 482 | 49.0 ms / 387 / 484 | - |
| `sam-vit-b` | kernels | 37.3 ms / 364 / 424 | 37.4 ms / 370 / 404 | 38.1 ms / 384 / 432 | - |
| `sam-vit-h` | portable | 216.1 ms / 1490 / 1882 | 215.4 ms / 1496 / 1902 | 215.7 ms / 1510 / 1916 | - |
| `sam-vit-h` | kernels | 143.6 ms / 1459 / 1712 | 144.4 ms / 1466 / 1704 | 145.1 ms / 1479 / 1714 | - |
| `sam-vit-l` | portable | 117.2 ms / 814 / 1052 | 116.5 ms / 820 / 1060 | 117.5 ms / 834 / 1048 | - |
| `sam-vit-l` | kernels | 82.0 ms / 812 / 930 | 81.6 ms / 818 / 946 | 83.2 ms / 833 / 922 | - |
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 reference 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| <= 3 % and p99 <= 15 % of the reference's median |value| (absolute error of the output `pred_masks`).

## Usage

```python
from fastforks import promptable_segmentation
model = promptable_segmentation.load("sam-vit-b")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg", input_points=[[x, y]], input_labels=[1])
result.masks  # [M, H, W] bool
# SAM 3 (text prompts): model("photo.jpg", text="coin") -> boxes, scores, masks
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: `sam-vit-b`, `sam-vit-h`, `sam-vit-l`.

## Kernels backend

`promptable_segmentation.load("sam-vit-b", mode="kernels")` runs our CUDA kernels (`dpt_fused`). 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 feccac41 (2026-11-06) -->

	---
	library_name: "fastforks"
	pipeline_tag: "mask-generation"
	license: "apache-2.0"
	tags:
	- "promptable_segmentation"
	- "segment-anything"
	- "promptable-segmentation"
	- "cuda"
	- "pytorch"
	- "fastforks"
	---
	# Segment Anything (SAM) (fastforks)

	Segment Anything (Kirillov et al. 2023): promptable segmentation with a ViT image encoder (windowed + global attention, relative positions) and a light prompt encoder / mask decoder; masks from points, boxes and mask logits. The portable `module()` is the image encoder only.

	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/facebookresearch/segment-anything> at `dca509f`.

	Task: promptable_segmentation. Tier: stable. Outputs: `pred_masks`, `iou_scores`. Backends: `portable`, `kernels`.

	Input: one image plus a point, box or text prompt. Output: masks with quality scores.

	## 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/promptable_segmentation/models/sam/card.toml).

	\| variant \| weights (author link) \| SHA-256 \| weights licence \| commercial use \|
	\|---\|---\|---\|---\|---\|
	\| `sam-vit-b@1` \| [sam_vit_b_01ec64.pth](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth) \| `ec2df6273261` \| Apache-2.0 \| yes \|
	\| `sam-vit-h@1` \| [sam_vit_h_4b8939.pth](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth) \| `a7bf3b02f3eb` \| Apache-2.0 \| yes \|
	\| `sam-vit-l@1` \| [sam_vit_l_0b3195.pth](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth) \| `3adcc4315b64` \| 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: `LICENSE`.

	Training data: SA-1B (11M licensed images, 1.1B automatically generated masks) per the paper; the dataset itself is under the SA-1B research licence.

	Licence evidence: https://github.com/facebookresearch/segment-anything/blob/main/README.md (License section: model checkpoints and code under Apache 2.0)

	## Input size

	any H x W >= 1, resized inside to the fixed encoder input 1024x1024 (the default export size)
	Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `sam-vit-b` 1080x1920 (0.4 GiB peak allocated, 0.5 reserved); `sam-vit-h` 1080x1920 (1.5 GiB peak allocated, 1.9 reserved); `sam-vit-l` 1080x1920 (0.8 GiB peak allocated, 1.0 reserved)

	## Speed and memory

	### Promptable segmentation, synthetic, 1024x1024

	\| model \| time (ms): original fp32 \| original \| portable \| kernels \| kernels speed-up: vs original \| vs portable \| peak memory (MiB, allocated / reserved): original \| portable \| kernels \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam-vit-b` \| 173 \| – \| 48.3 \| 37.0 \| – \| 1.3x \| – \| 378 / 420 \| 377 / 420 \|
	\| `sam-vit-h` \| 742 \| – \| 214 \| 143 \| – \| 1.5x \| – \| 1484 / 2524 \| 1480 / 1524 \|
	\| `sam-vit-l` \| 414 \| – \| 116 \| 81.5 \| – \| 1.4x \| – \| 833 / 1262 \| 831 / 862 \|

	### Startup and first call

	\| model \| load (s): original \| portable \| kernels \| first call (s): original \| portable \| kernels \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam-vit-b` \| 0.76 \| 0.46 \| 0.17† \| 0.27 \| 0.05† \| 0.04† \|
	\| `sam-vit-h` \| 3.53 \| 2.45 \| 0.89† \| 0.73 \| 0.21† \| 0.14† \|
	\| `sam-vit-l` \| 1.46 \| 1.21 \| 0.43† \| 0.42 \| 0.12† \| 0.08† \|

	### 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) \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam-vit-b` \| 1024x1024 \| 48.3 \| 40.9 \| 14.5 \| 27.3 \| 36 \| 37.0 \| 378 / 420 \| 362 / 400 \| 322 \|

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

	\| model \| mode \| 480x640 \| 720x1280 \| 1080x1920 \| 12 MP 3000x4000 \|
	\| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam-vit-b` \| portable \| 48.6 ms / 367 / 482 \| 48.6 ms / 374 / 482 \| 49.0 ms / 387 / 484 \| - \|
	\| `sam-vit-b` \| kernels \| 37.3 ms / 364 / 424 \| 37.4 ms / 370 / 404 \| 38.1 ms / 384 / 432 \| - \|
	\| `sam-vit-h` \| portable \| 216.1 ms / 1490 / 1882 \| 215.4 ms / 1496 / 1902 \| 215.7 ms / 1510 / 1916 \| - \|
	\| `sam-vit-h` \| kernels \| 143.6 ms / 1459 / 1712 \| 144.4 ms / 1466 / 1704 \| 145.1 ms / 1479 / 1714 \| - \|
	\| `sam-vit-l` \| portable \| 117.2 ms / 814 / 1052 \| 116.5 ms / 820 / 1060 \| 117.5 ms / 834 / 1048 \| - \|
	\| `sam-vit-l` \| kernels \| 82.0 ms / 812 / 930 \| 81.6 ms / 818 / 946 \| 83.2 ms / 833 / 922 \| - \|

	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 reference 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\| <= 3 % and p99 <= 15 % of the reference's median \|value\| (absolute error of the output `pred_masks`).

	## Usage

	```python
	from fastforks import promptable_segmentation

	model = promptable_segmentation.load("sam-vit-b") # mode="auto": the preferred backend from recorded measurements
	result = model("photo.jpg", input_points=[[x, y]], input_labels=[1])
	result.masks # [M, H, W] bool
	# SAM 3 (text prompts): model("photo.jpg", text="coin") -> boxes, scores, masks
	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: `sam-vit-b`, `sam-vit-h`, `sam-vit-l`.

	## Kernels backend

	`promptable_segmentation.load("sam-vit-b", mode="kernels")` runs our CUDA kernels (`dpt_fused`). 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 feccac41 (2026-11-06) -->