tests: add quantized attention tests (SDPA + eager) with MHA fusion c…

[yizhuoz004]

Description

Adds test_quantized_attention.py covering FP8 and INT8 PTQ via modelopt for both SDPA-based (VanillaAttention, GQAAttention) and hand-rolled eager attention (EagerAttention, mirroring HF ViT) patterns.

Test coverage:
_QuantAttentionMixin (SDPA, IAttentionLayer path):
- test_static: fixed shapes, causal/non-causal, LLM-realistic configs
- test_dynamic_batch / test_dynamic_seq: dynamic dims incl. decode (seq=1)
- test_edge_cases: single head, non-pow2 head_dim, causal prefill
- test_gqa: GQA/MQA with separate Q and KV head counts
- test_mha_kernel_precision: @expectedfailure (#4167) — MHA inputs are Half not FP8/Int8; normalization_quantize_scale not set in torch-trt

_EagerAttentionMixin (hand-rolled matmul+softmax+matmul):
- test_static: ViT-realistic shapes
- test_dynamic_seq: dynamic seq covering ViT patch-count range
- test_mha_kernel_precision: @expectedfailure (#4200) — TRT fuses into _gemm_mha_v2 but selects a Half tactic; quantizer scales don't reach the fused kernel boundary

MHA fusion check (_assert_mha_fused) matches both _gemm_mha (prefill) and _gemv_mha (decode) kernel prefixes.

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[meta-cla]

Hi @yizhuoz004!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!