7d6a98bc62
fix(framepack): use text_mask.device instead of hardcoded cuda
...
get_cu_seqlens creates a cu_seqlens tensor with device="cuda",
which crashes on non-CUDA devices (e.g. Ascend NPU raises
"Torch not compiled with CUDA enabled"). Create it on the same
device as the input text_mask instead, which is device-agnostic.
2026-09-12 09:08:48 +08:00
feeafc6286
strict ruff without exclude
...
Co-authored-by: Copilot <copilot@github.com >
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-05-11 08:36:49 +02:00
c8d6fd5cf8
Revert "much stricter ruff linting"
...
This reverts commit 310dbf1574
2026-05-11 08:13:57 +02:00
310dbf1574
much stricter ruff linting
...
Co-authored-by: Copilot <copilot@github.com >
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-05-11 07:15:37 +02:00
e5c494f999
cleanup logger
2026-02-19 11:09:13 +01:00
a3074baf8b
unified logger
2026-02-19 09:46:42 +01:00
bfe014f5da
modernize typing
2026-02-19 09:15:37 +01:00
0b3248c90a
fix framepack
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2025-10-31 11:08:27 -04:00
bd048e8efc
framepack: patch solver for unsupported gpus
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2025-09-26 12:28:52 -04:00
3087b8d8cd
Do not ignore offload with FramePack
2025-07-13 20:41:55 +03:00
c559e26616
add builtin framepack
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2025-07-08 15:47:07 -04:00
li-lizhe
Vladimir Mandic
Disty0