Fix environment setup for FP8

[yiliu30]

In case the user provides only QUANT_CONFIG without specifying quantization=inc.

[Copilot]

Pull request overview

This PR fixes environment setup for FP8 quantization to handle cases where users provide QUANT_CONFIG without explicitly specifying quantization=inc. The changes improve the robustness of quantization detection and use the correct inference-specific environment setup function.

Key Changes:

• Replace manual quantization type checking with a helper method _is_quant_with_inc()
• Update environment setup call from hpu_set_env() to hpu_inference_set_env()

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

✅ CI Passed

All checks passed successfully against the following vllm commit:
e924bbb4f4ac3258a71a18ac4c753c8056bc059f