[coloattention] coloattention support flash attention 2

[flybird11111]

📌 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

🚨 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

#4322

📝 What does this PR do?

Summarize your work here.
if you have any plots/diagrams/screenshots/tables, please attach them here.

Improved ColoAttention to utilize the latest flash attention 2:

1. flash_attn_func is used for attention with no paddings
2. Attention with paddings use SeqLenInfo, unpad, repad in order to work with flash_attn_varlen_func
3. Flash attention 2 only supports fp16/bf16 on Ampere or better GPUs. For other precisions or hardwares, we still use xformers to accelerate attention

💥 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.

[github-actions]

The code coverage for the changed files is 15%.

Click me to view the complete report

Name                                                       Stmts   Miss  Cover
------------------------------------------------------------------------------
colossalai/kernel/cuda_native/flash_attention.py             298    298     0%
colossalai/kernel/cuda_native/flash_attn/flash_attn_2.py      36     19    47%
colossalai/kernel/cuda_native/flash_attn/mem_eff_attn.py      33     25    24%
colossalai/kernel/cuda_native/scaled_softmax.py               96     65    32%
tests/test_utils/test_flash_attention.py                      92     62    33%
------------------------------------------------------------------------------
TOTAL                                                        555    469    15%

[github-actions]

The code coverage for the changed files is 33%.

Click me to view the complete report

Name                                                 Stmts   Miss  Cover
------------------------------------------------------------------------
colossalai/kernel/cuda_native/fmha/flash_attn_2.py      36     19    47%
colossalai/kernel/cuda_native/fmha/mem_eff_attn.py      33     25    24%
colossalai/kernel/cuda_native/scaled_softmax.py         96     65    32%
tests/test_utils/test_flash_attention.py                92     62    33%
------------------------------------------------------------------------
TOTAL                                                  257    171    33%

[flybird11111]

All tests have passed.