submission 523369
pank2025 · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 34 lines, June 9 Researcher Reciprocity License v1.0.
amd-mxfp4-mm.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-mxfp4-mm-523369?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 digestsha256:14b57dffd099655ca1f25248208d4126ad18b0fc17014768287c7c319ee5ccee
license declaredunknown
license concludedunknown
authorspank2025
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
amd-mxfp4-mm.py34 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)).
"""
import aiter
import torch
from aiter import QuantType, dtypes
from task import input_t, output_t
QUANT_FUNC = aiter.get_triton_quant(QuantType.per_1x32)
@torch.inference_mode()
def custom_kernel(data: input_t) -> output_t:
"""
Reference: MXFP4 per-1x32 quant on A; B_shuffle, B_scale_sh from generate_input.
gemm_a4w4 with bpreshuffle=True.
"""
A, _, _, B_shuffle, B_scale_sh = data
if not A.is_contiguous():
A = A.contiguous()
A_q, A_scale_sh = QUANT_FUNC(A, shuffle=True)
out_gemm = aiter.gemm_a4w4(
A_q,
B_shuffle,
A_scale_sh,
B_scale_sh,
dtype=dtypes.bf16,
bpreshuffle=True,
)
return out_gemm
scrolls · 34 lines total
Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0
Best evidence level for this revision: reported
JSON