[whjthu]

Summary

为 BGE embedding 和 reranker 补齐跨硬件的算子执行能力，使 InfiniTensor 能通过 InfiniOps 的公开接口完成检索 encoder 和分类头计算。

同时修复接入过程中暴露的外部内存、stream 顺序、输入约束和工作区分配问题，避免上层推理引擎为不同设备重复实现这些处理。

Motivation

知识库检索与精排需要执行词嵌入、归一化、attention、GELU 和分类头。现有算子已经覆盖大部分计算，但在 ONNX 语义、部分设备的类型转换，以及 ATen 与外部 runtime 配合执行方面仍有缺口。

本 PR 将这些能力和修复放在 InfiniOps 中，让调用方复用统一接口。模型加载、动态形状、文档检索和业务接口继续由上层实现。
Closes #

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

paste smoke test output here

Test Results on Supported Platforms

Platform	Affected	Build / Smoke Result	Full Result / Notes
NVIDIA
Iluvatar
MetaX
Cambricon
Moore
Ascend

Full `pytest` output (optional)

paste here

Benchmark / Performance Impact

Notes for Reviewers