68 Commits

Author	SHA1	Message	Date
doctorpangloss	3de77f6e24	ROCm support	2025-09-24 14:40:28 -07:00
doctorpangloss	85474cee78	Python 3.10 unit tests pass on NVIDIA containers and older torch	2025-09-24 14:39:52 -07:00
doctorpangloss	74d77a3757	Fix container image for rocm	2025-09-23 15:33:23 -07:00
doctorpangloss	6e98a0c478	Fix linting errors, preliminary rocm 7 support	2025-09-23 15:02:21 -07:00
doctorpangloss	2a881a768e	Fix #45 now test 3.10 and 3.12 images. NVIDIA doesn't support 3.11 at all!	2025-09-23 13:22:54 -07:00
doctorpangloss	ffbb2f7cd3	Fix bug in model_downloader	2025-09-18 14:47:28 -07:00
doctorpangloss	1cf77157a1	Enable inference tests in CI	2025-09-18 13:56:30 -07:00
doctorpangloss	b62d4f05e1	more type documentation, fix installation with dependency group	2025-09-08 11:35:19 -07:00
doctorpangloss	ac8e5aee7d	fix #42 install nightly for mps via comfyui[mps]@...	2025-07-16 21:15:00 -07:00
doctorpangloss	ff9832e6ba	fix macOS testing script	2025-07-16 15:58:13 -07:00
doctorpangloss	3ee969f778	Test macOS	2025-07-16 15:48:22 -07:00
doctorpangloss	3c5f477718	fix test	2025-07-16 15:26:19 -07:00
doctorpangloss	3ff24f0985	update dockerfile	2025-07-16 15:14:15 -07:00
doctorpangloss	25a0406b67	reduce metrics noise in tests	2025-07-15 14:08:46 -07:00
doctorpangloss	80b967364c	Fix tests	2025-07-15 10:48:11 -07:00
Benjamin Berman	fd5449c5b7	use newer image	2025-06-17 20:46:49 -07:00
Benjamin Berman	8e48a6765b	uv run tools	2025-05-21 09:54:39 -07:00
doctorpangloss	b799d59a19	include lockfile	2025-05-21 09:39:02 -07:00
Benjamin Berman	37f1f6697b	skip sageattention in ci	2025-05-19 23:15:22 -07:00
doctorpangloss	2bcfdbaa44	tweak test on our runners	2025-05-19 21:25:14 -07:00
doctorpangloss	351731557f	Use 3060 as runner	2025-05-19 20:26:51 -07:00
doctorpangloss	6d8deff056	Switch to uv for packaging	2025-05-19 15:58:08 -07:00
Benjamin Berman	c9598ec26d	include curl	2025-04-24 10:23:34 -07:00
Benjamin Berman	4015e59be5	update workflows and tweak installation script	2025-04-24 10:20:19 -07:00
Benjamin Berman	480b59b913	Migrate to pure pyproject.toml and uv for significantly faster and correct installation, add model paths for flux all in ones, and fix PathsList bug	2025-04-24 10:01:36 -07:00
Benjamin Berman	97400a679b	Disable ROCm again	2024-11-10 20:33:56 -08:00
Benjamin Berman	7587e42d8b	Re-enable ROCm tests	2024-10-17 11:16:17 -07:00
doctorpangloss	bbe2ed330c	Memory management and compilation improvements ... - Experimental support for sage attention on Linux - Diffusers loader now supports model indices - Transformers model management now aligns with updates to ComfyUI - Flux layers correctly use unbind - Add float8 support for model loading in more places - Experimental quantization approaches from Quanto and torchao - Model upscaling interacts with memory management better This update also disables ROCm testing because it isn't reliable enough on consumer hardware. ROCm is not really supported by the 7600.	2024-10-09 09:13:47 -07:00
doctorpangloss	253c021e77	Add more environment flags for ROCm	2024-09-13 09:02:47 -07:00
doctorpangloss	5d1eda7832	Try better ROCm configuration	2024-09-12 17:45:17 -07:00
doctorpangloss	ccdbd957ef	Fix pylint issues	2024-08-28 15:48:47 -07:00
Benjamin Berman	01feca812f	nf4 test and import module tweaks	2024-08-25 21:31:05 -07:00
doctorpangloss	653a970088	Fix tests, remove unsupported tests	2024-08-16 12:37:35 -07:00
Benjamin Berman	c6ce11b421	Switch to supported ROCm image	2024-07-30 11:42:14 -07:00
Benjamin Berman	5ff6b64459	Remove no longer supported ROCm	2024-07-30 11:25:49 -07:00
Benjamin Berman	38312e3c9f	Use updated containers for rocm to try to fix its crashes	2024-07-27 18:45:25 -07:00
Benjamin Berman	ac3a115d83	Re-enable ROCm tests	2024-07-19 23:16:39 -07:00
Benjamin Berman	adfee7d14d	No torchaudio	2024-07-19 20:44:36 -07:00
Benjamin Berman	c0c76ddbd5	Install torchaudio separately for the sake of completing the audio tests	2024-07-19 20:00:23 -07:00
doctorpangloss	87638da978	Include the testing environment	2024-07-18 17:16:26 -07:00
doctorpangloss	0c34c2b99d	Fix #13 audio nodes now work and test correctly	2024-07-18 17:15:44 -07:00
Benjamin Berman	e88f458a70	Enable macOS worker	2024-07-07 17:16:42 -07:00
doctorpangloss	1902aeee0b	Name this workflow better	2024-07-05 13:11:38 -07:00
doctorpangloss	7a20b189a5	Actually enable IPEX XPU support	2024-07-05 13:10:31 -07:00
doctorpangloss	5fef1e48f6	Test workflows	2024-07-05 11:41:50 -07:00
doctorpangloss	bb94b808dc	Improve automated test coverage	2024-07-05 11:11:21 -07:00
doctorpangloss	95d47276e9	Improve tests and distributed error notifications ... - Tests now perform faster - Tests will run on supported GPU platforms - Configuration has known issues related to setting up a working directory for an embedded client - Introduce a Skeletonize node that solves many problems with Canny - Improve behavior of exception reporting	2024-07-04 10:16:02 -07:00
doctorpangloss	1980c5f236	Use an image with earlier drivers	2024-06-28 18:15:33 -07:00
doctorpangloss	a485782029	Add lora test prefixed with test_ so that pytest can find it	2024-06-28 17:13:18 -07:00
doctorpangloss	7f81b8345d	Subtle test gathering bug that will have to be investigated	2024-06-28 17:12:06 -07:00