G4 passes at 6.184x once the gate and up projections reach the device

[bsbodden]

Same model, same prompts, same --arm both protocol as the 2026-10-07-g4-dispatch baseline. The PTX module is byte-identical across both runs (kernel sha256 4c534e62… either side), so nothing in the device code moved and the comparison isolates the routing.

	baseline	dual path routed	delta
accelerated decode	9.02 tok/s	31.26 tok/s	+246.6%
control decode	5.05 tok/s	5.06 tok/s	+0.2%
G4	1.788x — FAILED	6.184x — PASSED	gate 3.00x
qualified	false	true
launches / decode step	241.0	321.0	+33.2%
transfers / decode step	402.0	522.0	+29.9%
Q4_K projections per layer	4.05	6.07	predicted 6.00

The control arm moving 0.2% is what makes the rest readable: the denominator is stable, so the accelerated arm's 3.47x is not a quieter host.

The dispatch cost rose and it did not matter

33% more launches and 30% more transfers bought a 3.47x faster arm, because the two projections that moved are 53.3% of a layer's projection arithmetic. Reading 1.788x as a dispatch ceiling was wrong — dispatch was not the binding constraint there, an unimplemented code path was.

Q4_K/DECODE_PROJECTION per layer landing on 6.07 against the 6.00 predicted from the GGUF header confirms the dual path is taken, independent of any timing.

Correctness is not the claim

TensorOps.ggufDualMatmul computed those projections on the CPU and produced right answers — slower, not wrong. This change has no correctness credit and would have earned nothing had the speed not moved. It is kept because 31.26 beats 9.02, and for no other reason.

Also fixes the half of #237 this run exposed as useless

CudaRoutingCounters.declined was added and incremented, but CudaKernelGateCli.Routing never serialised it — so the run printed totalDeclinedProjections = None. The counter built to make a silent fallback visible was itself invisible in the artifact. Routing now carries declinedProjections and totalDeclinedProjections, verified off-device against a real report.

Still open

522 transfers per decode step moving 15.4 MB remains the standing overhead — but it now sits on an arm passing its gate at 2.06x the threshold, so device-resident activations should be weighed against G1 rather than assumed next.

G1 is untouched. This run reports tokenParity: null and says nothing about the attention argmax. The path passes G4 and still cannot ship.

:backend-cuda:check and :models-bench:check green: 50 and 269 tests, zero failures.