[CORE] support for *.pt type prompt adapters

[prashantgupta24]

Support *.pt type prompt adapters.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which consists a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of default ones by unblocking the steps in your fast-check build on Buildkite UI.

Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge).

To run full CI, you can do one of these:

• Comment /ready on the PR
• Add ready label to the PR
• Enable auto-merge.

🚀

[g-eoj]

This is nice! FYI, the OpenAI entrypoint will have issues:

vllm/vllm/entrypoints/openai/serving_engine.py

Lines 91 to 102 in 2f808e6

	if prompt_adapters is not None:
	for i, prompt_adapter in enumerate(prompt_adapters, start=1):
	with pathlib.Path(prompt_adapter.local_path,
	"adapter_config.json").open() as f:
	adapter_config = json.load(f)
	num_virtual_tokens = adapter_config["num_virtual_tokens"]
	self.prompt_adapter_requests.append(
	PromptAdapterRequest(
	prompt_adapter_name=prompt_adapter.name,
	prompt_adapter_id=i,
	prompt_adapter_local_path=prompt_adapter.local_path,
	prompt_adapter_num_virtual_tokens=num_virtual_tokens))

[prashantgupta24]

Closing for now, decision was made internally about monkey-patching this functionality instead