sam2 / README.md

fastforks 0.1.0

ba6c3fe 2 days ago

7.61 kB

---
library_name: "fastforks"
pipeline_tag: "mask-generation"
license: "apache-2.0"
tags:
- "promptable_segmentation"
- "segment-anything"
- "promptable-segmentation"
- "cuda"
- "pytorch"
- "fastforks"
---
# Segment Anything 2.1 (SAM 2.1), image (fastforks)

Segment Anything 2.1 (Ravi et al. 2024), image mode: promptable segmentation with a hierarchical Hiera image encoder, an FPN neck and the SAM prompt encoder / mask decoder with high-resolution skip features; masks from points, boxes and mask logits (no video memory). 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/sam2> at `2b90b9f`.

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/sam2/card.toml).
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
| `sam2.1-hiera-base-plus@1` | [sam2.1_hiera_base_plus.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_base_plus.pt) | `a2345aede871` | Apache-2.0 | yes |
| `sam2.1-hiera-large@1` | [sam2.1_hiera_large.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt) | `2647878d5dfa` | Apache-2.0 | yes |
| `sam2.1-hiera-small@1` | [sam2.1_hiera_small.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_small.pt) | `6d1aa6f30de5` | Apache-2.0 | yes |
| `sam2.1-hiera-tiny@1` | [sam2.1_hiera_tiny.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_tiny.pt) | `7402e0d864fa` | 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 and the SA-V video dataset (plus internal data) per the paper; SA-V itself is under CC BY 4.0, SA-1B under its research licence.
Licence evidence: https://github.com/facebookresearch/sam2/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): `sam2.1-hiera-base-plus` 1080x1920 (0.4 GiB peak allocated, 0.6 reserved); `sam2.1-hiera-large` 1080x1920 (0.7 GiB peak allocated, 0.9 reserved); `sam2.1-hiera-small` 1080x1920 (0.3 GiB peak allocated, 0.4 reserved); `sam2.1-hiera-tiny` 1080x1920 (0.3 GiB peak allocated, 0.4 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 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `sam2.1-hiera-base-plus` | 102 | – | 32.0 | 25.1 | – | 1.3x | – | 412 / 464 | 426 / 524 |
| `sam2.1-hiera-large` | 243 | – | 68.0 | 48.8 | – | 1.4x | – | 742 / 768 | 760 / 828 |
| `sam2.1-hiera-small` | 68.5 | – | 18.8 | 15.6 | – | 1.2x | – | 318 / 366 | 330 / 386 |
| `sam2.1-hiera-tiny` | 61.3 | – | 16.6 | 13.9 | – | 1.2x | – | 304 / 382 | 316 / 362 |
### Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- |
| `sam2.1-hiera-base-plus` | 0.53 | 0.43 | 0.19† | 0.10 | 0.03† | 0.03† |
| `sam2.1-hiera-large` | 2.92 | 1.10 | 0.39† | 0.24 | 0.07† | 0.05† |
| `sam2.1-hiera-small` | 0.32 | 0.36 | 0.13† | 0.07 | 0.02† | 0.02† |
| `sam2.1-hiera-tiny` | 0.41 | 0.25 | 0.11† | 0.13 | 0.02† | 0.01† |
### 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) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `sam2.1-hiera-tiny` | 1024x1024 | 16.6 | 14.2 | 13.4 | 8.6 | 34 | 13.9 | 304 / 382 | 270 / 322 | 266 |
### Fixed-size speed and peak memory, all models
| model | mode | 480x640 | 720x1280 | 1080x1920 | 12 MP 3000x4000 |
| --- | --- | --- | --- | --- | --- |
| `sam2.1-hiera-base-plus` | portable | 32.0 ms / 395 / 540 | 31.9 ms / 402 / 558 | 32.1 ms / 415 / 568 | - |
| `sam2.1-hiera-base-plus` | kernels | 25.1 ms / 408 / 472 | 25.1 ms / 415 / 490 | 25.3 ms / 428 / 472 | - |
| `sam2.1-hiera-large` | portable | 68.2 ms / 724 / 936 | 68.6 ms / 732 / 948 | 68.3 ms / 745 / 954 | - |
| `sam2.1-hiera-large` | kernels | 48.7 ms / 742 / 824 | 48.7 ms / 750 / 836 | 49.0 ms / 763 / 842 | - |
| `sam2.1-hiera-small` | portable | 18.7 ms / 298 / 420 | 19.1 ms / 305 / 422 | 18.9 ms / 319 / 426 | - |
| `sam2.1-hiera-small` | kernels | 15.4 ms / 310 / 356 | 15.5 ms / 317 / 358 | 15.6 ms / 331 / 346 | - |
| `sam2.1-hiera-tiny` | portable | 16.7 ms / 285 / 410 | 16.6 ms / 292 / 410 | 16.8 ms / 305 / 426 | - |
| `sam2.1-hiera-tiny` | kernels | 13.8 ms / 296 / 346 | 13.8 ms / 304 / 346 | 14.0 ms / 317 / 346 | - |
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("sam2.1-hiera-base-plus")  # 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: `sam2.1-hiera-base-plus`, `sam2.1-hiera-large`, `sam2.1-hiera-small`, `sam2.1-hiera-tiny`.

## Kernels backend

`promptable_segmentation.load("sam2.1-hiera-base-plus", 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 2.1 (SAM 2.1), image (fastforks)

	Segment Anything 2.1 (Ravi et al. 2024), image mode: promptable segmentation with a hierarchical Hiera image encoder, an FPN neck and the SAM prompt encoder / mask decoder with high-resolution skip features; masks from points, boxes and mask logits (no video memory). 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/sam2> at `2b90b9f`.

	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/sam2/card.toml).

	\| variant \| weights (author link) \| SHA-256 \| weights licence \| commercial use \|
	\|---\|---\|---\|---\|---\|
	\| `sam2.1-hiera-base-plus@1` \| [sam2.1_hiera_base_plus.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_base_plus.pt) \| `a2345aede871` \| Apache-2.0 \| yes \|
	\| `sam2.1-hiera-large@1` \| [sam2.1_hiera_large.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt) \| `2647878d5dfa` \| Apache-2.0 \| yes \|
	\| `sam2.1-hiera-small@1` \| [sam2.1_hiera_small.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_small.pt) \| `6d1aa6f30de5` \| Apache-2.0 \| yes \|
	\| `sam2.1-hiera-tiny@1` \| [sam2.1_hiera_tiny.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_tiny.pt) \| `7402e0d864fa` \| 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 and the SA-V video dataset (plus internal data) per the paper; SA-V itself is under CC BY 4.0, SA-1B under its research licence.

	Licence evidence: https://github.com/facebookresearch/sam2/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): `sam2.1-hiera-base-plus` 1080x1920 (0.4 GiB peak allocated, 0.6 reserved); `sam2.1-hiera-large` 1080x1920 (0.7 GiB peak allocated, 0.9 reserved); `sam2.1-hiera-small` 1080x1920 (0.3 GiB peak allocated, 0.4 reserved); `sam2.1-hiera-tiny` 1080x1920 (0.3 GiB peak allocated, 0.4 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 \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam2.1-hiera-base-plus` \| 102 \| – \| 32.0 \| 25.1 \| – \| 1.3x \| – \| 412 / 464 \| 426 / 524 \|
	\| `sam2.1-hiera-large` \| 243 \| – \| 68.0 \| 48.8 \| – \| 1.4x \| – \| 742 / 768 \| 760 / 828 \|
	\| `sam2.1-hiera-small` \| 68.5 \| – \| 18.8 \| 15.6 \| – \| 1.2x \| – \| 318 / 366 \| 330 / 386 \|
	\| `sam2.1-hiera-tiny` \| 61.3 \| – \| 16.6 \| 13.9 \| – \| 1.2x \| – \| 304 / 382 \| 316 / 362 \|

	### Startup and first call

	\| model \| load (s): original \| portable \| kernels \| first call (s): original \| portable \| kernels \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam2.1-hiera-base-plus` \| 0.53 \| 0.43 \| 0.19† \| 0.10 \| 0.03† \| 0.03† \|
	\| `sam2.1-hiera-large` \| 2.92 \| 1.10 \| 0.39† \| 0.24 \| 0.07† \| 0.05† \|
	\| `sam2.1-hiera-small` \| 0.32 \| 0.36 \| 0.13† \| 0.07 \| 0.02† \| 0.02† \|
	\| `sam2.1-hiera-tiny` \| 0.41 \| 0.25 \| 0.11† \| 0.13 \| 0.02† \| 0.01† \|

	### 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) \|
	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam2.1-hiera-tiny` \| 1024x1024 \| 16.6 \| 14.2 \| 13.4 \| 8.6 \| 34 \| 13.9 \| 304 / 382 \| 270 / 322 \| 266 \|

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

	\| model \| mode \| 480x640 \| 720x1280 \| 1080x1920 \| 12 MP 3000x4000 \|
	\| --- \| --- \| --- \| --- \| --- \| --- \|
	\| `sam2.1-hiera-base-plus` \| portable \| 32.0 ms / 395 / 540 \| 31.9 ms / 402 / 558 \| 32.1 ms / 415 / 568 \| - \|
	\| `sam2.1-hiera-base-plus` \| kernels \| 25.1 ms / 408 / 472 \| 25.1 ms / 415 / 490 \| 25.3 ms / 428 / 472 \| - \|
	\| `sam2.1-hiera-large` \| portable \| 68.2 ms / 724 / 936 \| 68.6 ms / 732 / 948 \| 68.3 ms / 745 / 954 \| - \|
	\| `sam2.1-hiera-large` \| kernels \| 48.7 ms / 742 / 824 \| 48.7 ms / 750 / 836 \| 49.0 ms / 763 / 842 \| - \|
	\| `sam2.1-hiera-small` \| portable \| 18.7 ms / 298 / 420 \| 19.1 ms / 305 / 422 \| 18.9 ms / 319 / 426 \| - \|
	\| `sam2.1-hiera-small` \| kernels \| 15.4 ms / 310 / 356 \| 15.5 ms / 317 / 358 \| 15.6 ms / 331 / 346 \| - \|
	\| `sam2.1-hiera-tiny` \| portable \| 16.7 ms / 285 / 410 \| 16.6 ms / 292 / 410 \| 16.8 ms / 305 / 426 \| - \|
	\| `sam2.1-hiera-tiny` \| kernels \| 13.8 ms / 296 / 346 \| 13.8 ms / 304 / 346 \| 14.0 ms / 317 / 346 \| - \|

	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("sam2.1-hiera-base-plus") # 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: `sam2.1-hiera-base-plus`, `sam2.1-hiera-large`, `sam2.1-hiera-small`, `sam2.1-hiera-tiny`.

	## Kernels backend

	`promptable_segmentation.load("sam2.1-hiera-base-plus", 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) -->