Module gpu 

GPU-accelerated matching via wgpu. GPU-accelerated batch inference for the MoE classifier via wgpu compute shaders.

Processes N feature vectors in a single GPU dispatch, achieving ~10-100x throughput over CPU for large batches. Falls back to CPU when no GPU is available or for batches smaller than the crossover threshold.

Architecture mirrors ml_scorer.rs exactly:

• Gate: Linear(55→6) + softmax
• 6 experts: Linear(55→32)+ReLU → Linear(32→16)+ReLU → Linear(16→1)
• Output: sigmoid(weighted sum of expert logits)

Feature-gating in the lean build

Every entry point that would touch wgpu / vyre-driver-wgpu directly is wrapped in #[cfg(feature = "gpu")]. With the gpu feature off (the cargo install keyhog --no-default-features --features ci path), the GPU drivers aren’t linked at all, the probe functions report “no GPU available” without ever calling into wgpu, and the self-test functions return a “not available in this build” Err instead of panicking. The CPU MoE path in ml_scorer.rs is the entire scoring story under that profile.

Structs

GpuRegionPresencePeerSelfTest

One acquired peer proven by the production GPU region-presence self-test.

GpuRegionPresenceSelfTest

Status report from the production GPU region-presence self-test.

GpuRegionPresenceSelfTestFailure

Honest aggregate failure from the peer self-test.

GpuSelfTest

Result from an explicit GPU adapter and dispatch self-test.

VyreGpuSelfTest

Result from an explicit VYRE GPU scanner self-test.

Enums

GpuRuntimePolicy

Functions

gpu_available

Return true when GPU scoring support is available in this build/runtime.

gpu_region_presence_self_test

Build a minimal one-detector CompiledScanner and dispatch a scan through the production GPU backend. A PASS proves device acquisition, compilation, lowering, dispatch, and host readback on this host.

gpu_required_by_policy

True when the resolved runtime policy demands a usable GPU and a silent CPU fallback is forbidden.

gpu_runtime_policy

The current process-wide GPU runtime policy.

gpu_self_test

Force a GPU compute dispatch and validate the returned scores.

require_gpu_preflight

Require-GPU preflight, independent of backend routing.

set_gpu_runtime_policy

Set the process-wide GPU runtime policy (Auto/On/Off) consulted by backend routing and GPU init.

vyre_gpu_self_test

Force the VYRE GPU scanner and coalesced scanner paths.