[WebGPU] Add gating logic for subgroup shuffle primitives

[ksgr5566]

Summary

This adds gating logic on top of apache#17699 to support optional subgroup shuffle
primitives based on a compile-time flag.

Problem

The PR apache#17699 always generates subgroup shuffle ops when targeting WebGPU.
However, not all WebGPU devices support subgroups. We need a way to:

• Default to shared memory reductions (universally compatible)
• Optionally enable subgroup shuffles for devices that support them

Solution

Implement gating via TVM target parameter:

• Default thread_warp_size=1 disables warp reductions (uses shared memory + barriers)
• Add target parser UpdateWebGPUAttrs() that sets thread_warp_size=32 when supports_subgroups=true
• Add --enable-subgroups CLI flag in mlc-llm to surface the option to users

The gating happens at the reduction path selection level (IsWarpReduction() in
lower_thread_allreduce.cc), ensuring subgroup ops are never generated unless explicitly enabled.

Changes

• TVM: Target parser + default thread_warp_size=1
• MLC-LLM: --enable-subgroups flag ([WebGPU] Add --enable-subgroups flag for optional subgroup support mlc-ai/mlc-llm#3431)
• WebLLM: WGSL shader dumping for verification

Testing

Tested with Llama-3.2-1B-q4f16_1. Baseline (no flag) uses shared memory reductions;
with flag, generates subgroupShuffle* ops.
Both the generated WGSLs here: https://gist.github.com/ksgr5566/301664a5dda3e46f44092be4d09b2d4f