shared_expert_e4m3

Function shared_expert_e4m3 

Source
pub fn shared_expert_e4m3() -> bool
Expand description

2026-09-29: Whether the Nemotron-H shared expert’s prefill runs the E4M3 tile GEMM. Off unless the serve published otherwise: the checkpoint’s precision (NVFP4 weights, 16-bit activations on the BF16-MMA w4a16_gemm) is the default.