Skip to main content

GPU_WAIT_COUNT

Static GPU_WAIT_COUNT 

Source
pub static GPU_WAIT_COUNT: AtomicU64
Expand description

Decode-profiler: count of GPU submit → poll(Maintain::Wait) round-trips. Incremented by QTensorEngine::poll_wait (every native blocking sync point routes through it); read/reset by the bench to derive per-token synchronization overhead.