submission 572866
n8_gr8_ · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 69 lines, June 9 Researcher Reciprocity License v1.0.
submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-amd-moe-mxfp4-572866?include=source"interfacepython
Compatibility
measured onAMD Instinct MI355X
declared hardwareAMD Instinct MI355X
architecturesgfx950
dtypesbf16, fp32, fp8_e8m0, int32, 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 digestsha256:6c27595b9d9dc546c5757a3b94faa29f9b1eda03b715a885a81f8d1e48f92dbd
license declaredunknown
license concludedunknown
authorsn8_gr8_
imported2026-08-15
Kernel source
submission.py69 lines
#!POPCORN leaderboard amd-moe-mxfp4
#!POPCORN gpu MI355X
import os
os.environ["HIP_FORCE_DEV_KERNARG"] = "1"
os.environ["AITER_USE_OPUS_MOE_SORTING"] = "1"
os.environ["AITER_LOG_LEVEL"] = "ERROR"
os.environ["AITER_USE_NT"] = "1"
import torch
from task import input_t, output_t
from aiter import ActivationType, QuantType
from aiter.fused_moe import fused_moe
@torch.inference_mode()
def custom_kernel(data: input_t) -> output_t:
(
hidden_states,
gate_up_weight, down_weight,
gate_up_weight_scale, down_weight_scale,
gate_up_weight_shuffled, down_weight_shuffled,
gate_up_weight_scale_shuffled, down_weight_scale_shuffled,
topk_weights, topk_ids, config,
) = data
hidden_pad = config["d_hidden_pad"] - config["d_hidden"]
intermediate_pad = config["d_expert_pad"] - config["d_expert"]
bs = config["bs"]
n_routed = config["n_routed_experts"]
d_expert = config["d_expert"]
if bs >= 512:
os.environ.pop("AITER_BYPASS_TUNE_CONFIG", None)
if n_routed > 32:
os.environ["AITER_KSPLIT"] = "2"
elif d_expert >= 2048:
os.environ["AITER_KSPLIT"] = "1"
else:
os.environ.pop("AITER_KSPLIT", None)
elif bs >= 128:
os.environ["AITER_BYPASS_TUNE_CONFIG"] = "1"
if n_routed > 32:
os.environ["AITER_KSPLIT"] = "4"
else:
os.environ["AITER_KSPLIT"] = "2"
else:
os.environ["AITER_BYPASS_TUNE_CONFIG"] = "1"
if n_routed > 32:
os.environ["AITER_KSPLIT"] = "4"
else:
os.environ["AITER_KSPLIT"] = "2"
return fused_moe(
hidden_states,
gate_up_weight_shuffled, down_weight_shuffled,
topk_weights, topk_ids,
expert_mask=None,
activation=ActivationType.Silu,
quant_type=QuantType.per_1x32,
doweight_stage1=False,
w1_scale=gate_up_weight_scale_shuffled,
w2_scale=down_weight_scale_shuffled,
a1_scale=None, a2_scale=None,
hidden_pad=hidden_pad,
intermediate_pad=intermediate_pad,
)
scrolls · 69 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