[Polish] Polish error message

[Jiang-Jia-Jun]

Motivation

Modifications

Usage or Command

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ Jiang-Jia-Jun
❌ jiangjiajun
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot]

Thanks for your contribution!

[Copilot]

Pull Request Overview

This PR polishes error messages and refactors logger usage throughout the codebase. The primary goals are to improve error message clarity when KV cache resources are insufficient and standardize logger usage by replacing the generic logger with more specific llm_logger and console_logger instances.

Key changes:

• Replaced assertion with explicit error handling and improved error message for KV cache resource exhaustion
• Standardized logger usage across the config module by replacing logger with llm_logger and console_logger
• Added support for a new splitwise version (v2) with router and local scheduler configuration
• Suppressed paddleformers INFO-level logging by setting log level to ERROR

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.

File	Description
fastdeploy/config.py	Refactored logger usage from generic logger to specific llm_logger/console_logger; improved KV cache error message with actionable information; added v2 splitwise configuration support with validation; added innode_prefill_ports parameter support
fastdeploy/init.py	Changed paddleformers logger level from INFO to ERROR to suppress less critical logs; added warning filter for paddleformers module