| Port details |
- py-comfy-kitchen ComfyUI: Fast kernel library for Diffusion inference
- 0.2.16 misc
 =0      0.2.14Version of this port present on the latest quarterly branch. - Maintainer: yuri@FreeBSD.org
- Port Added: 2026-03-19 06:48:24
- Last Update: 2026-07-02 05:05:20
- Commit Hash: 6521e8f
- Also Listed In: python
- License: APACHE20
- WWW:
- https://github.com/Comfy-Org/comfy-kitchen
- Description:
- Comfy Kitchen is a high-performance kernel library designed for Diffusion model
inference. It provides optimized implementations for critical operations,
including various quantization formats and Rotary Positional Embeddings (RoPE).
The library features a flexible dispatch system that automatically selects the
most efficient compute backend—CUDA, Triton, or eager PyTorch—based on available
hardware and input constraints.
Key features include:
* Optimized kernels specifically tuned for Diffusion inference workloads.
* Support for multiple compute backends (CUDA C, Triton JIT, and pure PyTorch).
* Transparent quantization via a QuantizedTensor subclass that intercepts
PyTorch operations.
* Support for advanced quantization formats including FP8, NVFP4, and MXFP8.
* Automatic backend selection and constraint validation for hardware-specific
optimizations.
* Implementation of performance-critical functions like RoPE and scaled matrix
multiplication.
  ¦  ¦  ¦  ¦ 
- Manual pages:
- FreshPorts has no man page information for this port.
- pkg-plist: as obtained via:
make generate-plist - There is no configure plist information for this port.
- USE_RC_SUBR (Service Scripts)
- no SUBR information found for this port
- Dependency lines:
-
- ${PYTHON_PKGNAMEPREFIX}comfy-kitchen>0:misc/py-comfy-kitchen@${PY_FLAVOR}
- To install the port:
- cd /usr/ports/misc/py-comfy-kitchen/ && make install clean
- To add the package, run one of these commands:
- pkg install misc/py-comfy-kitchen
- pkg install py312-comfy-kitchen
NOTE: If this package has multiple flavors (see below), then use one of them instead of the name specified above.
NOTE: This is a Python port. Instead of py312-comfy-kitchen listed in the above command, you can pick from the names under the Packages section.- PKGNAME: py312-comfy-kitchen
- Package flavors (<flavor>: <package>)
- py312: py312-comfy-kitchen
- distinfo:
- TIMESTAMP = 1782967439
SHA256 (Comfy-Org-comfy-kitchen-v0.2.16_GH0.tar.gz) = 931a5bdd5f3fdc40357f64603929a2db3f3a08e868f34686773db507a37f7bee
SIZE (Comfy-Org-comfy-kitchen-v0.2.16_GH0.tar.gz) = 193591
Packages (timestamps in pop-ups are UTC):
- Dependencies
- NOTE: FreshPorts displays only information on required and default dependencies. Optional dependencies are not covered.
- Build dependencies:
-
- py312-nanobind>=2.0.0 : devel/py-nanobind@py312
- py312-setuptools>0 : devel/py-setuptools@py312
- py312-wheel>0 : devel/py-wheel@py312
- python3.12 : lang/python312
- py312-build>=0 : devel/py-build@py312
- py312-installer>=0 : devel/py-installer@py312
- Test dependencies:
-
- py312-pytest>=7,1 : devel/py-pytest@py312
- python3.12 : lang/python312
- Runtime dependencies:
-
- py312-pytorch>=2.5.0 : misc/py-pytorch@py312
- python3.12 : lang/python312
- This port is required by:
- for Run
-
- misc/comfyui
Configuration Options:- No options to configure
- Options name:
- misc_py-comfy-kitchen
- USES:
- python
- FreshPorts was unable to extract/find any pkg message
- Master Sites:
|
| Commit History - (may be incomplete: for full details, see links to repositories near top of page) |
| Commit | Credits | Log message |
|---|
0.2.16
02 Jul 2026 05:05:20
 |
Yuri Victorovich (yuri) |
misc/py-comfy-kitchen: update 0.2.14 → 0.2.16 |
0.2.14
29 Jun 2026 05:55:32
|
Yuri Victorovich (yuri) |
misc/py-comfy-kitchen: update 0.2.10 → 0.2.14 |
0.2.10
02 Jun 2026 07:06:48
|
Yuri Victorovich (yuri) |
misc/py-comfy-kitchen: update 0.2.9 → 0.2.10 |
0.2.9
30 May 2026 02:32:43
|
Yuri Victorovich (yuri) |
misc/py-comfy-kitchen: update 0.2.8 → 0.2.9 |
0.2.8
19 Mar 2026 06:47:38
|
Yuri Victorovich (yuri) |
misc/py-comfy-kitchen: New port: ComfyUI: Fast kernel library for Diffusion
inference |
As an Amazon Associate I earn from qualifying purchases.