feat(cambricon): add Copy implementation

[baominghelly]

Summary

• Add a CNNL-based Cambricon provider for Copy using cnnlCopy_v2.
• Add reusable Cambricon CNNL/CNRT resource helpers and extend Copy coverage for scalar tensors and strided KV-cache slices.

Motivation

Cambricon currently has no native provider for the non-deprecated Copy operator. This prevents layout-preserving, broadcast, and strided-output copy paths from running through InfiniOps on MLU devices.

Type of Change

• feat - new feature / new operator / new platform
• fix - bug fix
• perf - performance improvement (no behavioral change)
• refactor - code restructuring without behavior change
• test - adding or fixing tests only
• docs - documentation only
• build / ci - build system or CI configuration
• chore - tooling, formatting, or other non-code changes
• Breaking change (requires a ! in the Conventional Commits prefix or a BREAKING CHANGE: footer)

Platforms Affected

• CPU (WITH_CPU)
• NVIDIA (WITH_NVIDIA)
• Iluvatar (WITH_ILUVATAR)
• MetaX (WITH_METAX)
• Cambricon (WITH_CAMBRICON)
• Moore (WITH_MOORE)
• Ascend (WITH_ASCEND)
• PyTorch C++ bindings (WITH_TORCH)
• Build system / CMake / CI
• Python bindings / user-facing API

Smoke Test Result

The standard smoke set was not run because its operator allowlist does not include copy. A Copy-only Cambricon build passed:

cmake -S /workspace/src/InfiniOps-upstream \
  -B /workspace/build/infiniops-upstream \
  -DINFINI_OPS_OPS=copy
cmake --build /workspace/build/infiniops-upstream --parallel 32

[1/3] Building CXX object .../generated_dispatch_0.cc.o
[2/3] Building CXX object .../copy.cc.o
[3/3] Linking CXX shared module src/ops.cpython-310-x86_64-linux-gnu.so

Test Results on Supported Platforms

Platform	Affected	Build / Smoke Result	Full Result / Notes
NVIDIA	No	N/A - not affected	N/A - not affected
Iluvatar	No	N/A - not affected	N/A - not affected
MetaX	No	N/A - not affected	N/A - not affected
Cambricon	Yes	Targeted build passed; standard smoke not run	42 targeted Copy tests passed
Moore	No	N/A - not affected	N/A - not affected
Ascend	No	N/A - not affected	N/A - not affected

Targeted pytest output

python -m pytest tests/test_copy.py -q --devices cambricon

..........................................                               [100%]
42 passed in 0.25s

Benchmark / Performance Impact

N/A. This adds a previously missing Cambricon provider and does not change an existing implementation.

Notes for Reviewers

• The provider supports scalar, broadcast, non-contiguous input, and strided output tensors, including KV-cache slice writes.
• CNNL execution uses the caller's queue and validates caller-provided workspace capacity.
• The CNNL/CNRT RAII helper names are aligned with feat(cambricon): add Embedding implementation #926; this PR extends tensor descriptor setup to scalar tensors and the 64-bit cnnlSetTensorDescriptorEx_v2 interface.
• No deprecated RearrangeInfinilm provider is added.