Won-Kyu Park

support loading libtcmalloc_minimal.dll for windows

1

## Description The effectiveness of tcmalloc has been discussed in several other threads. For Windows, `LD_PRELOAD` is not available, but the `tcmalloc_minimal` module supported by gperftool can be compiled with...

use empty_like to reduce model loading time

1

use `empty_like()` instead of `zeros_like()` in the `LoadStateDictOnMeta()` we don't have to initialize params with zeros, It will be overwrittened by `param.copy_(input_param)`, (https://github.com/pytorch/pytorch/blob/main/torch/nn/modules/module.py#L2441 ) ## Checklist: - [x] I have...

fix RestrictedUnpickler

3

it does no harm to remove the pytorch_lightening dependency in the safe.py (torch.load) see also https://github.com/comfyanonymous/ComfyUI/commit/735ac4cf81862b21902b312930ebfc92eef63357 ## Checklist: - [x] I have read [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) - [x] I have...

fix lowvram error

4

fix `NotImplementedError: Cannot copy out of meta tensor; no data!` this error triggered by changing model when user use `--medvram` and `--medvarm-sdxl` ## reproduce condition 1. `sd_checkpoints_limit = 1` (Maximum...

extension installer using threadpoolexecutor

4

## Description - [x] parallelize `run_extension_installer()` using `ThreadPoolExecutor()` ## Notes: - webui have `args.skip_prepare_environment` option. so, `install.py` should have independent behavior of its execution order. - `max_workers=1` to use normal...

reduce script extensions loading time using threadpoolexecutor

3

## Description * [x] reduce script extensions loading time using ThreadPoolExecutor * at loading extension modules step, it could be parallelized. * [x] add `script_loading_max_thread` "System" option. (set max thread...

based on https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/modules_forge/main_thread.py original author's comment in the source code: > This file is the main thread that handles all gradio calls for major t2i or i2i processing. > Other...

support cuda malloc

5

imported from comfy: https://github.com/comfyanonymous/ComfyUI/blob/f1d6cef71c70719cc3ed45a2455a4e5ac910cd5e/cuda_malloc.py original commits: - https://github.com/comfyanonymous/ComfyUI/commit/799c08a: Auto disable cuda malloc on some GPUs on windows. - https://github.com/comfyanonymous/ComfyUI/commit/D39c58b: Disable cuda malloc on GTX 750 Ti. - https://github.com/comfyanonymous/ComfyUI/commit/85a8900: Disable cuda...

bump pillow version, pre-commit to dev

3

- [x] bump pillow version to `11.3.0` (fix pyproject.toml and run `poetry update pillow`) - [x] pre-commit to dev group - [x] add `[project]` section to support both uv and...

### 작업 개요 * [x] `_get()` 오류 수정 : 참조 https://github.com/iamport/iamport-rest-client-python/issues/57 ### 작업 분류 - [x] 버그 수정