[aciddelgado]

Description

Fix the CUDA QMoE packed-INT GEMV path's remaining reference to the removed
routing_record API and add a focused expert-counting regression.

• Capture selected expert IDs immediately after routing and consume the snapshot
  before the packed-INT path returns, using the same lifecycle as the neighboring
  paths. Preserve the existing non-plugin/non-minimal guards.
• Add MoeExpertCountingTest.CudaQMoEPackedIntGemv: FP16, INT2, fused SwiGLU,
  three rows, four experts, top-k 1, 512-wide hidden/intermediate dimensions,
  and block size 64.
• Verify expert-dependent numerical outputs and per-invocation selection counters:
  duplicate routes [0, 0, 2], a repeated invocation, then changed routes
  [1, 1, 1]. Expected counters are [0.1, 0, 0.1, 0],
  [0.19, 0, 0.19, 0], and [0.171, 0.1, 0.171, 0].
• Disable CPU fallback and cap dense dequantization scratch at one byte, so a
  successful run cannot silently use the dense fallback.

Only moe_quantization.cc and moe_expert_counting_test.cc change. Routing
selection and GEMV arithmetic are unchanged; no WebGPU/PagedAttention changes
are included.

Validation

Built and executed locally on NVIDIA A100-SXM4-80GB (SM80), CUDA 12.8.93,
GCC 11.4, cuDNN 9.10.2.21, Release, warnings-as-errors, QUICK_BUILD=OFF.
The existing CUDA build tree was reconfigured from SM86 to SM80, recompiling
the CUDA targets. This is not a claim of CUDA 13/GCC 14 CI validation.

After configuring with the same options plus --update, the following build
command passed:

source /workspace/venv/bin/activate
python tools/ci_build/build.py \
  --build_dir /workspace/onnxruntime/build/cuda-ci-20260929 \
  --config Release --build --parallel 16 --cmake_generator Ninja \
  --build_shared_lib --build_wheel --enable_onnx_tests --use_cuda \
  --use_binskim_compliant_compile_flags --nvcc_threads 4 --flash_nvcc_threads 4 \
  --cuda_version=12.8 --cuda_home=/usr/local/cuda-12.8 \
  --cudnn_home=/workspace/venv/lib/python3.11/site-packages/nvidia/cudnn \
  --enable_cuda_profiling --skip_tests --allow_running_as_root \
  --targets onnxruntime_test_all onnxruntime_provider_test \
  --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=80 \
  onnxruntime_BUILD_UNIT_TESTS=ON \
  onnxruntime_ENABLE_CUDA_EP_INTERNAL_TESTS=ON \
  onnxruntime_BUILD_CUDA_QUANT_PREPROCESS=ON

Tests were run from the build output directory:

cd /workspace/onnxruntime/build/cuda-ci-20260929/Release
export LD_LIBRARY_PATH=/workspace/venv/lib/python3.11/site-packages/nvidia/cudnn/lib:/usr/local/cuda-12.8/lib64:${LD_LIBRARY_PATH:-}

./onnxruntime_test_all --gtest_filter='MoeExpertCountingTest.CudaQMoE*'
# PASS: 4 tests, no skips.

./onnxruntime_provider_test --gtest_filter='MoETest.QMoETest_Int2CudaPackedDecodeMultiRowExpertParity'
# PASS: 1 test, no skips.

ORT_ENABLE_QMOE_KERNEL_DEBUG_INFO=1 ./onnxruntime_test_all \
  --gtest_filter='MoeExpertCountingTest.CudaQMoEPackedIntGemv'
# PASS: 1 test; all three invocations log Route=packed_int_gemv Rows=3.

Negative control: temporarily omitted both packed-path Capture and
Consume, rebuilt with
cmake --build build/cuda-ci-20260929/Release --target onnxruntime_providers_cuda --parallel 16,
and ran
./onnxruntime_test_all --gtest_filter='MoeExpertCountingTest.CudaQMoEPackedIntGemv'.
It failed as intended: outputs still matched, but seven counter assertions
failed because all counters remained zero (first failure: expert 0 expected
0.1, actual 0). Restored the repair, rebuilt the provider, and reran both
focused suites: all five tests passed. No negative-control edits are committed.

Motivation and Context

The expert-counting migration in #32738 left a stale routing_record->CaptureTile
call in the packed-INT GEMV early-return path. This prevents ordinary built-in
CUDA compilation on current main; simply deleting that call would compile but
silently omit expert counts for this path.

This separates the repair originally included in #32808, following
the scope/coverage review comment.
The production patch is carried unchanged from commit 1f57e92abe; the new
regression verifies the runtime counting behavior as well as compilation.
After this lands, merging main into #32808 will remove the unrelated MoE file
from that PR's diff.

[Copilot]

Copilot review overview

🟢 Approval recommended

The narrow lifecycle fix matches neighboring paths and is covered by targeted numerical and counter assertions.

Review effort: Balanced
Findings: None

What changed in this PR

Fixes CUDA QMoE packed-INT GEMV expert counting and adds focused regression coverage.

Changes:

• Captures and consumes routed expert snapshots using the established lifecycle.
• Tests repeated and changed routing while preventing CPU/dense fallback.

File	Description
onnxruntime/​contrib_ops/​cuda/​moe/​moe_quantization.cc	Repairs expert snapshot handling.
onnxruntime/​test/​framework/​moe_expert_counting_test.cc	Adds packed-INT counting regression.

---

💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[aciddelgado]

Copilot resolve the merge conflicts in this pull request

[Copilot]

Copilot resolve the merge conflicts in this pull request

Merged main and resolved the test conflict, retaining the PR's more comprehensive packed-INT regression. Merge commit: d2b730f6.