Sufiyan Adhikari

@Zburatorul Added example showing how to use the changes from this PR. I have personally been using this for more than a month now, where I make my transactions through...

@krrishdholakia The outputs for the same input are different. in litellm I am consistently getting longer output and hence the time is higher. might be because of different prompt translation...

for this to work, the vllm docker needs `--lora-modules name1=/path/to/adapter1 name2=hfuser/adapter2`. So you see, the adapter path either can be a local path or huggingface model. since there's no way...