MIOpen Error: 83cd7bbb1465:/rocm-libraries/projects/miopen/src/fusion.cpp:1224: The provided workspace size is less than required. Req:328859648 Given:0
MIOpen error: 3

import sys
import torch

try:
    import fused_conv_bias_relu
except ImportError as e:
    print("SKIP: Apex fused ops not available:", e)
    sys.exit(0)

# Raw Apex API: forward([x, weight, bias], padding, stride) -> list[tensor]
def run(name, x, w, b, pad=1, stride=1):
    try:
        fused_conv_bias_relu.forward([x, w, b], pad, stride)
        fused_conv_bias_relu.forward_no_relu([x, w, b], pad, stride)
        print(f"  {name}: OK")
        return True
    except Exception as e:
        print(f"  {name}: FAIL — {e}")
        return False

def main():
    bs, c, hw = 2, 256, 7
    x_nchw = torch.rand(bs, c, hw, hw, dtype=torch.half).cuda()
    x_nhwc = x_nchw.to(memory_format=torch.channels_last)
    w = torch.rand(256, c, 3, 3, dtype=torch.half).cuda().to(memory_format=torch.channels_last)
    b = torch.rand(1, 256, 1, 1, dtype=torch.half).cuda().to(memory_format=torch.channels_last)

    print("ConvBiasReLU + ConvBias layout test (fp16, bs=2, 256x7x7):")
    run("channels_last (NHWC)", x_nhwc, w, b)
    run("channels_first (NCHW)", x_nchw, w, b)

if __name__ == "__main__":
    main()

PRETTY_NAME="Ubuntu 24.04.3 LTS"
NAME="Ubuntu"
VERSION_ID="24.04"
VERSION="24.04.3 LTS (Noble Numbat)"
VERSION_CODENAME=noble

====================================== Product Info ======================================
GPU[0]          : Card Series:          AMD Instinct MI355X
GPU[0]          : Card Model:           0x75a3
GPU[0]          : Card Vendor:          Advanced Micro Devices, Inc. [AMD/ATI]
GPU[0]          : Card SKU:             N/A
GPU[0]          : Subsystem ID:         0x75a3
GPU[0]          : Device Rev:           0x00
GPU[0]          : Node ID:              3
GPU[0]          : GUID:                 42583
GPU[0]          : GFX Version:          gfx950
(GPU[1-7] are the same)