submission 581779
Infatoshi · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 23 lines, June 9 Researcher Reciprocity License v1.0.
submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-mxfp4-mm-581779?include=source"interfacepython
Compatibility
measured onAMD Instinct MI355X
declared hardwareAMD Instinct MI355X
architecturesgfx950
dtypesbf16, mxfp4
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Reported · How evidence levels are derived →
Source and license
sourceavailable
revision digestsha256:dc63cff54d1ee0bcafd40b063d57bab8ef87679ef366a0ca64696f77980b48f4
license declaredunknown
license concludedunknown
authorsInfatoshi
imported2026-08-26
Kernel source
submission.py23 lines
#!POPCORN leaderboard amd-mxfp4-mm
#!POPCORN gpu MI355X
import torch
import aiter
from aiter import dtypes
from aiter.ops.triton.quant import dynamic_mxfp4_quant
from aiter.utility.fp4_utils import e8m0_shuffle
from task import input_t, output_t
def _quant_mxfp4(x, shuffle=True):
x_fp4, bs_e8m0 = dynamic_mxfp4_quant(x)
if shuffle:
bs_e8m0 = e8m0_shuffle(bs_e8m0)
return x_fp4.view(dtypes.fp4x2), bs_e8m0.view(dtypes.fp8_e8m0)
def custom_kernel(data: input_t) -> output_t:
a, b, b_q, b_shuffle, b_scale_sh = data
A_q, A_scale_sh = _quant_mxfp4(a.contiguous(), shuffle=True)
return aiter.gemm_a4w4(A_q, b_shuffle, A_scale_sh, b_scale_sh, dtype=dtypes.bf16, bpreshuffle=True)
Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0
Best evidence level for this revision: reported
JSON