hidden_states.float() and gate_bf16.T.float() create new FP32 tensors
during CUDA graph capture, which is not graph-capturable.
Fix: run the linear in BF16 (Blackwell tensor cores handle BF16 natively),
then convert only the output logits to FP32 for numerical stability
in sqrt(softplus). The single logits.float() is graph-capturable
because it's a unary op with a pre-existing output buffer.
biondizzle
ffa7842b58