Amitg1

Hey, Great work! Proctor looks like a great framework. 2 questions here: 1. is the project still in maintenance? active development? 2. in the presentation (https://engineering.indeedblog.com/talks/managing-experiments-behavior-dynamically-proctor/, slide 49), sample size...

Question: Can i use airflow operators with CWL-Airflow?

1

Can I use airflow operators with CWL-Airflow? or only cmdtools like in CWL? if so, how I am expected to push new operators or cmdtools to Airflow? Thanks! great job.

### Feature request use peft to load and unload lora models. Use pipe.enable_lora() or pipe.disable_lora() instead of pipe.load_lora_weights()` and pipe.unload_lora_weights() ### Motivation - today bentoml diffusers code is using pipe.unload_lora_weights()...

feature: use LoRA as entity in bentoml model store

1

### Feature request We are using diffusers SDXL + LoRA Potentially we gonna have lots of LoRA files that we want to manage. we would like to be able to...

bug: Custom exception using FastAPI mount does not work as expected

1

### Describe the bug Hello, Currently, the Bento REST API handles inference issues, such as IO errors or GPU out-of-memory errors, by returning a 500 internal server error to the...

Update examples to use onediffx

1

Update examples to use onediffx specifically [text_to_image_sdxl_reuse_pipe](https://github.com/siliconflow/onediff/blob/main/onediff_diffusers_extensions/examples/text_to_image_sdxl_reuse_pipe.py) lines 126-133 - how to load load_state_dict into specific components when using `from onediff.infer_compiler import oneflow_compile` instead of ``` compiled_unet = oneflow_compile(base.unet) base.unet...