xycdx 7aef554d83 add torch implementation for interpolation ...

- Implement bilinear interpolation kernel using Numba
- Benchmark shows 2x speedup compared to CPU version
- Closes #817

2025-09-10 20:39:35 +08:00

..

configs

wans2v inference

2025-08-27 11:51:56 +08:00

controlnets

Revert "Wan refactor"

2025-06-11 17:29:27 +08:00

data

wans2v inference

2025-08-27 11:51:56 +08:00

distributed

fix usp dit_forward

2025-07-30 19:21:21 +08:00

extensions

add torch implementation for interpolation

2025-09-10 20:39:35 +08:00

lora

rearrange lora loading modules

2025-07-24 18:56:25 +08:00

models

support s2v framepack

2025-09-01 16:48:46 +08:00

pipelines

support direct distill

2025-09-09 16:12:31 +08:00

processors

Revert "Wan refactor"

2025-06-11 17:29:27 +08:00

prompters

Revert "Wan refactor"

2025-06-11 17:29:27 +08:00

schedulers

qwen-image

2025-08-04 20:24:13 +08:00

tokenizer_configs

load hunyuani2v model

2025-03-07 17:43:30 +08:00

trainers

merge data process to training script

2025-09-04 15:18:56 +08:00

utils

add inpaint mask in qwen-image

2025-08-18 15:16:38 +08:00

vram_management

Qwen-Image FP8 (#761)

2025-08-07 16:56:02 +08:00

__init__.py

rebuild base modules

2024-07-26 12:15:40 +08:00