Joe

`proxy` environment vars

Repro of behavior. Server is running on local but app can't find it and gets stuck. ``` ❯ export http_proxy= ❯ wave run steam_stats.py INFO: Will watch for changes in...

Hi @mturoci, I tried your repro file and still got the error. Here's a better description of the error, see the "not found" messages and file contents: Here's the file...

per @mmalohlava request we should try to document mojo scoring with sparkling water on spectrum conductor.

per @mmalohlava request putting this here: https://www.ibm.com/developerworks/community/blogs/281605c9-7369-46dc-ad03-70d9ad377480/entry/Submitting_Batch_Spark_Applications_to_IBM_Platform_Conductor?lang=en

The README still needs work but I think I addressed all the other comments.

@osery sorry I didn't respond to that message sooner. The motivation comes from multiple support requests for a method to do local multi-threaded predictions with the mojo scorer. @mmalohlava suggested...

Hi @SwapnilDreams100, I have an initial implementation of adapter support for the OpenAI entry points based on https://github.com/SwapnilDreams100/vllm/tree/main. Would you be open to me contributing to your PR?

@SwapnilDreams100 openai entrypoint PR (https://github.com/SwapnilDreams100/vllm/pull/2) is ready for an initial review. @SwapnilDreams100 @Yard1 if prompt adapters and lora modules can be used at the same time, should the model list...

If `max_prompt_adapter_tokens` is less than `num_virtual_tokens`, there is an error like: ``` RuntimeError: The expanded size of the tensor (10) must match the existing size (128) at non-singleton dimension 0....