For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

fp8_gemv_kernel

def fp8_gemv_kernel[c_type: DType, c_layout: TensorLayout, a_layout: TensorLayout, w_layout: TensorLayout, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None]](c: TileTensor[c_type, c_layout, MutAnyOrigin], a: TileTensor[DType.bfloat16, a_layout, ImmutAnyOrigin], weight: TileTensor[DType.float8_e4m3fn, w_layout, ImmutAnyOrigin], n: Int, k: Int)

One warp per output column; 32 lanes stride down K widening FP8 -> f32.

c is [1, N], a the bf16 activation [1, K], weight the FP8-E4M3 weight [N, K]. Accumulation is fp32. Produces the RAW x @ W_fp8^T; the per-tensor scalar weight_scale is folded post-matmul by the graph lowering.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit