submission 581693
chrysostom_d · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 24 lines, June 9 Researcher Reciprocity License v1.0.
submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-mxfp4-mm-581693?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:a193e5637c0cfe1b4eda4e2f5cf84a0b984cc0d87c11167ce9cd6181f4633d4b
license declaredunknown
license concludedunknown
authorschrysostom_d
imported2026-08-26
Techniques
Extracted from the mirrored source by pattern, never inferred. Each row cites its line.
fp4
FP4 quant + FP4 GEMM reference: bf16 A, MXFP4 B -> MXFP4 per-1x32 quant A -> gemm_a4w4 -> bf16 C.Kernel source
submission.py24 lines
"""
FP4 quant + FP4 GEMM reference: bf16 A, MXFP4 B -> MXFP4 per-1x32 quant A -> gemm_a4w4 -> bf16 C.
Quant logic follows aiter op_tests/test_gemm_a4w4.py (get_triton_quant(QuantType.per_1x32)).
"""
from task import input_t, output_t
import aiter
from aiter import dtypes
from aiter.ops.triton.quant import dynamic_mxfp4_quant
from aiter.utility.fp4_utils import e8m0_shuffle
def custom_kernel(data: input_t) -> output_t:
A, _B, _Bq, B_shuffle, B_scale_sh = data
A_q, A_scale = dynamic_mxfp4_quant(A)
A_scale_sh = e8m0_shuffle(A_scale)
return aiter.gemm_a4w4(
A_q.view(dtypes.fp4x2),
B_shuffle,
A_scale_sh.view(dtypes.fp8_e8m0),
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