[Inference] Refactor modeling attention layer by abstracting attention backends

[char-1ee]

📌 Checklist before creating the PR

• I have created an issue for this PR for traceability
• The title follows the standard format: [doc/gemini/tensor/...]: A concise description
• I have added relevant tags if possible for us to better distinguish different PRs
• I have installed pre-commit: pip install pre-commit && pre-commit install

🚨 Issue number

Link this PR to your issue with words like fixed to automatically close the linked issue upon merge

e.g. fixed #1234, closed #1234, resolved #1234

📝 What does this PR do?

1. Refactor inference modeling files:
   Current modeling under colossalai/inference have nested if-else conditional checks on choosing cuda/triton kernels for Attention layer computations. This PR abstracts the positional encoding and KV Cache operations into PreAttentionBackend, flash attention and flash decoding ops into AttentionBackend. Now inference modeling initializes attention backend according to configs that users give.

2. Fix typo and naming, refactor code organizations.

Tests:

💥 Checklist before requesting a review

• I have linked my PR to an issue (instruction)
• My issue clearly describes the problem/feature/proposal, with diagrams/charts/table/code if possible
• I have performed a self-review of my code
• I have added thorough tests.
• I have added docstrings for all the functions/methods I implemented

⭐️ Do you enjoy contributing to Colossal-AI?

• 🌝 Yes, I do.
• 🌚 No, I don't.

Tell us more if you don't enjoy contributing to Colossal-AI.