Function batched_embed_fp8 

pub fn batched_embed_fp8(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    token_ids_dev: DevicePtr,
    embed_table: DevicePtr,
    row_scale: DevicePtr,
    output: DevicePtr,
    num_tokens: u32,
    hidden_size: u32,
    stream: u64,
) -> Result<()>

2026-09-25: batched_embed over an FP8 E4M3 table with one f32 scale per row (the quantize_bf16_to_fp8 layout); rows are dequantized to BF16 on read.