leslie-fang-intel

import requests
import torch
print(torch.__version__, flush=True)
import torch.nn as nn
import os, pickle
import numpy as np 
import torch._inductor.config as config
import torch._dynamo.config as dynamo_config
import gc
import time

leslie-fang-intel

# AOT ID: ['0_inference']
from ctypes import c_void_p, c_long, c_int
import torch
import math
import random
import os
import tempfile
from math import inf, nan
from cmath import nanj
from torch._inductor.hooks import run_intermediate_hooks

leslie-fang-intel

import torch
import torch._inductor.config as config

config.freezing = True

in_feature = 32
out_feature = 64
q_min, q_max = -32, 31
reshape_a = True
expand_a_scale = False

leslie-fang-intel

import requests
import torch
print(torch.__version__)
import torch.nn as nn
import os, pickle
import numpy as np 
import torch._inductor.config as config

config.freezing = True
config.freezing_discard_parameters = True

leslie-fang-intel

#include "/tmp/torchinductor_leslie/3b/c3bi5gk6mslf6u4iaqafhxm64z6u65e3eain4xlary5blqnvv6xx.h"
#include <c10/util/Unroll.h>
#include <torch/csrc/inductor/aoti_torch/c/shim.h>



template <int64_t BLOCK_M, int64_t BLOCK_N, bool accum>
inline void kernel_micro_gemm_kernel(
    const float* __restrict__ A,

leslie-fang-intel

import torch
from torch._inductor import config

batch_size = 4
in_features = 512
out_features = 1024
dtype = torch.bfloat16
# dtype = torch.float16
bias = True

leslie-fang-intel

import torch
from torch._inductor.codecache import CppWrapperCodeCache

cpp_wrapper_src = (
'''
#include <optional>
#include <Python.h>

leslie-fang-intel

# AOT ID: ['0_inference']
from ctypes import c_void_p, c_long, c_int
import torch
import math
import random
import os
import tempfile
from math import inf, nan
from torch._inductor.hooks import run_intermediate_hooks
from torch._inductor.utils import maybe_profile

leslie-fang-intel

# AOT ID: ['0_inference']
from ctypes import c_void_p, c_long, c_int
import torch
import math
import random
import os
import tempfile
from math import inf, nan
from torch._inductor.hooks import run_intermediate_hooks
from torch._inductor.utils import maybe_profile

leslie-fang-intel

# AOT ID: ['0_inference']
from ctypes import c_void_p, c_long, c_int
import torch
import math
import random
import os
import tempfile
from math import inf, nan
from torch._inductor.hooks import run_intermediate_hooks
from torch._inductor.utils import maybe_profile