[None][perf] Custom decode kernels for MinimaxM3 - rebased

[brb-nv]

Description

This MR adds a few custom decode kernels for MinimaxM3 ported from vLLM.

• The CuteDSL indexer decode kernel and corresponding tests were originally contributed by @gau-nernst here: [M3] Improve indexer for long-context decode (sm100) vllm-project/vllm#48582
• The triton sparse attn decode kernel and corresponding tests were originally contributed by @youkaichao here: [Model] Add MiniMax M3 support vllm-project/vllm#45381
• Some of the cute utils have been originally contributed by @gau-nernst here:
  [GDN] GDN Prefill kernel for SM100 vllm-project/vllm#43273
  [M3] Improve indexer for long-context decode (sm100) vllm-project/vllm#48582

Special thanks to the original contributors!

Test Coverage

$ pytest tests/integration/defs/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_nvfp4[use_msa=True-eval_mode=default] -s -v

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[brb-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #63868 [ run ] triggered by Bot. Commit: 0332348 Link to invocation

[tensorrt-cicd]

PR_Github #63868 [ run ] completed with state SUCCESS. Commit: 0332348
/LLM/main/L0_MergeRequest_PR pipeline #51807 completed with status: 'SUCCESS'

CI Report

Link to invocation

[peihu-nv]

LGTM