trunk/96600b6cc815b5b6c7c8db104fafb6e77dc69e88: [Native DSL] Share topk policy across JIT and AOT (#196599)
- PyTorch: 1096 events in the last 90 days
- PyTorch: 1083th Release in the last 90 days
- Previous: earlier the same day · viable/strict/1789653042
What happened
Human Notes: Match JIT and AOT conditionals, unify expected coverage. Codex: Make the torch-free AOT declaration the shared source of truth for topk dtype, capability, K, N, and work-rung selection. JIT now imports that policy, gains the measured SM90 and bfloat16 regimes, and uses the same dynamic-N kernel variants as AOT. Replace the exact-N AOT grid with runtime-N radix kernels and one K=16 register branch ladder…
Summary assembled by rule from the sources below