Module exec 

2026-09-30: How a weight-reading node executes its DECLARED formats on a device. The declared precision is never changed here; what varies per device is the instruction that carries it:

• the activation format picks the MMA kind (BF16 activations: BF16 MMA, any weight format widened in registers; FP8: the FP8 MMA; NVFP4: the block-scaled FP4 MMA);
• a device without the FP4 MMA but with the FP8 one runs NVFP4 operands through the exact E2M1 -> E4M3 conversion ((q & 0x80808080) | ((q & 0x70707070) >> 2) is value x 2^-6 for all 16 codes; the 2^6 folds into the group scale), block scales applied in FP32 per K=16 step: the same products as the declared W4A4, not an upcast;
• anything else has no path, which the plan states.

A device’s instruction is not enough: a node runs on the FP4 MMA only where the device’s class compiles an FP4 block-scale kernel for it (super::avail::without_fp4_kernel); elsewhere it takes the same path as on a device without that MMA. node_exec is the one answer per node: the report’s execution columns, its “FP4 costing” row and every node’s cost read it.

Owner: metrale-circuit (hardware). Invariants: no silent upcast. An activation format with no native or exact path is Exec::NoPath, never re-planned at a wider format.

Enums

Exec

2026-09-30: The execution of one node’s declared formats.

Functions

exec_of

2026-09-30: How device executes a node of weight reading activation. NVFP4 weights under FP8 activations (W4A8 with group-16 E4M3 scales) have no single-instruction MMA on any device unless native_mma says so (fp4_fp8_nvfp4_scaled); they take the exact E4M3 path.

fp4_fallback

2026-10-01: How device runs an NVFP4 activation without an FP4 block-scale kernel: on the FP8 MMA through the exact conversion where it has one, else no path; Exec::NoFp4Kernel when the device has the FP4 MMA and only the kernel is missing.

kind_of

2026-09-30: The MMA kind the activation format needs.

node_exec

2026-10-01: How node n of c runs on device (weight-reading nodes only): its declared formats on the device’s instructions (exec_of), or fp4_fallback when the class compiles no FP4 block-scale kernel for it (no_fp4_kernel).

pair_name

2026-09-30: The declared pair as W4A16-style text.