[bugfix] fix bugs in vllm_v1_adapter.py and setup.py && format code

[zhuofan1123]

No description provided.

[Copilot]

Pull Request Overview

This PR addresses bugs in the FlexKV integration setup and vLLM adapter by fixing path handling and string formatting issues. The changes improve robustness of the build configuration and resolve logging inconsistencies.

• Fixed path handling in setup.py to use absolute paths for include directories
• Corrected a mathematical calculation bug in token matching logic
• Standardized logging messages to remove unnecessary f-string formatting

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
setup.py	Uses absolute path for include directories to ensure proper build configuration
flexkv/integration/vllm/vllm_v1_adapter.py	Fixes token calculation bug and removes unnecessary f-string formatting from log messages

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

[nitpick] The expression request.num_prompt_tokens+1 should have spaces around the + operator for better readability: request.num_prompt_tokens + 1.

Suggested change

	num_tokens_to_get = (cdiv(request.num_prompt_tokens+1, self.block_size)-1)*self.block_size
	num_tokens_to_get = (cdiv(request.num_prompt_tokens + 1, self.block_size)-1)*self.block_size