[Build] Fix cuda packaging build error

[tianleiwu]

Description

Fixes the CUDA packaging pipeline build error (with CUDA arch 52-real) that was introduced by #29451.

Root cause

The small-M batched GEMV path added in #29451 defines half helpers for the batched kernel — the Acc2<half> accumulator trait and the PackNatural / DotAccum / HorizontalAdd overloads — inside a single #if (!defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 530) guard that compiles the entire declaration out for archs below sm_53.

However, MatMulFloat4BatchedKernel<half> is launched from host code and is therefore instantiated for every target architecture, including sm_52. During the sm_52 device pass those half helpers no longer exist, so nvcc reported (100 errors, e.g.):

• incomplete type "Acc2<half>" is not allowed
• no suitable user-defined conversion from "WPack<half>" to "const WPack<nv_bfloat16>" exists (the compiler fell back to the nv_bfloat16 overloads)

Fix

Mirror the existing nv_bfloat16 convention in the same file: always define the type and function signatures, and gate only the arch-specific (half2-intrinsic) bodies. Now Acc2<half> is always a complete type and the half overloads always exist, so MatMulFloat4BatchedKernel<half> compiles for sm_52. On archs below sm_53 the bodies compile to no-ops (returning zeros), which matches the already-shipped nv_bfloat16 behavior for archs below sm_80.

Motivation and Context

The CUDA packaging pipeline builds with CMAKE_CUDA_ARCHITECTURES=52-real;61-real;75-real;86-real;89-real;90-virtual, so the sm_52 device pass is required and the pipeline was broken by #29451.

[Copilot]

Pull request overview

This PR aims to fix CUDA packaging pipeline build failures when compiling for sm_52 (“52-real”), introduced by PR #29451, by ensuring certain half2-based helper signatures are available even when the half2-intrinsic implementations are not.

Changes:

• Removes/relaxes __CUDA_ARCH__ >= 530 gating around some half-specific helper type definitions.
• Refactors half helper functions (PackNatural, DotAccum, HorizontalAdd) so their signatures are always present while their bodies are conditionally compiled.