[BFCL] Support for pre-existing completion endpoint

[ThomasRochefortB]

URL Endpoint Support for BFCL

This PR is a product of the discussion in #850.

Description

This PR adds support for using pre-existing OpenAI-compatible endpoints in BFCL, allowing users to bypass the built-in vLLM/sglang server setup. This is particularly useful for distributed environments like SLURM clusters where model serving and benchmarking need to be handled as separate jobs.

Changes

• Added --skip-server-setup flag to CLI
• Added environment variable support for endpoint configuration:
  • VLLM_ENDPOINT (defaults to 'localhost')
  • VLLM_PORT (defaults to existing VLLM_PORT constant)
• Modified OSSHandler to support external endpoints
• Updated documentation for new configuration options

Usage

Users can now specify custom endpoints in two ways:

1. Using environment variables:

export VLLM_ENDPOINT="custom.host.com"
export VLLM_PORT="8000"

2. Using a .env file:

VLLM_ENDPOINT=custom.host.com
VLLM_PORT=8000

Then run BFCL with the --skip-server-setup flag:

python -m bfcl generate --model MODEL_NAME --backend vllm --skip-server-setup

Related Issue

Closes #850

[HuanzhiMao]

Thanks for the PR @ThomasRochefortB !

[sghyan16]

hi, I followed the instruction Using a .env file and use --skip-server-setup flag, but I encountered a problem that when I specify the MODEL_NAME, An error occured:

zz-8444 is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`

[HuanzhiMao]

hi, I followed the instruction Using a .env file and use --skip-server-setup flag, but I encountered a problem that when I specify the MODEL_NAME, An error occured:

zz-8444 is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`

Hey @sghyan16 ,
Could you open a issue for this and attach the console output as well? Thank you!