feat(build): select operator implementations from ops.json

[voltjia]

Summary

• Extends INFINI_OPS_OPS so it accepts a user-owned ops.json that selects exact implementation slots per operator.
• Uses one normalized selection for wrapper generation, linked dependency resolution, and generated Torch operators.
• Preserves the existing comma-separated operator allowlist and legacy external header-list JSON format, including structured {path, backend} descriptors.
• Removes the need for a separate INFINI_OPS_LINKED_OPS configuration surface.

Example:

{
  "add": {"implementations": [0]},
  "argmax": {"implementations": [8]},
  "top_k_top_p_sampling_from_logits": {"implementations": [16]}
}

Motivation

Operator names alone cannot express builds that need one implementation while excluding another provider of the same operator. Selecting by the existing implementation slot keeps native, generated Torch, Triton, and linked providers under the same configuration model and avoids resolving or linking unselected external dependencies.

Compatibility

• -DINFINI_OPS_OPS=add,gemm retains its current operator-level behavior.
• -DINFINI_OPS_OPS=/absolute/path/ops.json enables slot selection.
• A repository-root user ops.json remains supported when the CMake option is unset.
• The repository does not ship a default ops.json; the file is a consumer-owned build input.
• Slot arrays are sets, not priority lists. Runtime default selection remains the first active slot.
• Legacy string/string-array header paths and structured {path, backend} descriptors remain supported.

Validation

• Ruff format/check passed.
• Focused parser/resolver tests: 50 passed.
• Wrapper and Torch codegen tests: 59 passed; the packaged-ATen case requiring torchgen is covered by the hosted NVIDIA build.
• Concrete CMake configurations cover inline precedence, JSON slot filtering, missing external providers, linked slot resolution, and implementation-header reconfigure dependencies.
• Hosted documentation, Ruff, clang-format, NVIDIA, Iluvatar, MetaX, Moore, and Cambricon checks passed before the documentation-only wording clarification; current-head checks are running.
• The previous Ascend shadow task timed out after 3600 seconds waiting for an Ascend device (resource_timeout); the regular Ascend job was cancelled in the same device-lease window. Neither reached selector compilation or tests.
• The selector commit is based directly on master and does not contain feat(nvidia): add top-k top-p sampling provider #922.

Notes

This replaces #923, which GitHub automatically closed when its head branch was renamed to align the branch type with the feat(build) title.

The FlashInfer sampling provider remains a separate stacked change in #930.