tsvisab

[Bug]: Assertion on "meta-llama/Meta-Llama-3-70B-Instruct" when calling in async manner

1

### Your current environment ```text PyTorch version: 2.2.1+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OS: Debian GNU/Linux 11 (bullseye) (x86_64)...

Allow specifying `adapter_id` on `chat/completions` requests

4

### Feature request It seems that if i want to load a base model with an adapter and consume it, i'll have to use the `generate` route only which allows...