Upload ./cpp_kernels.py with huggingface_hub
Browse files- cpp_kernels.py +55 -0
cpp_kernels.py
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from torch.utils import cpp_extension
|
2 |
+
import pathlib
|
3 |
+
import os
|
4 |
+
import subprocess
|
5 |
+
|
6 |
+
def _get_cuda_bare_metal_version(cuda_dir):
|
7 |
+
raw_output = subprocess.check_output([cuda_dir + "/bin/nvcc", "-V"],
|
8 |
+
universal_newlines=True)
|
9 |
+
output = raw_output.split()
|
10 |
+
release_idx = output.index("release") + 1
|
11 |
+
release = output[release_idx].split(".")
|
12 |
+
bare_metal_major = release[0]
|
13 |
+
bare_metal_minor = release[1][0]
|
14 |
+
|
15 |
+
return raw_output, bare_metal_major, bare_metal_minor
|
16 |
+
|
17 |
+
def _create_build_dir(buildpath):
|
18 |
+
try:
|
19 |
+
os.mkdir(buildpath)
|
20 |
+
except OSError:
|
21 |
+
if not os.path.isdir(buildpath):
|
22 |
+
print(f"Creation of the build directory {buildpath} failed")
|
23 |
+
|
24 |
+
# Check if cuda 11 is installed for compute capability 8.0
|
25 |
+
cc_flag = []
|
26 |
+
_, bare_metal_major, bare_metal_minor = _get_cuda_bare_metal_version(cpp_extension.CUDA_HOME)
|
27 |
+
if int(bare_metal_major) >= 11:
|
28 |
+
cc_flag.append('-gencode')
|
29 |
+
cc_flag.append('arch=compute_80,code=sm_80')
|
30 |
+
if int(bare_metal_minor) >= 7:
|
31 |
+
cc_flag.append('-gencode')
|
32 |
+
cc_flag.append('arch=compute_90,code=sm_90')
|
33 |
+
|
34 |
+
# Build path
|
35 |
+
srcpath = pathlib.Path(__file__).parent.absolute()
|
36 |
+
buildpath = srcpath / 'build'
|
37 |
+
_create_build_dir(buildpath)
|
38 |
+
|
39 |
+
def _cpp_extention_load_helper(name, sources, extra_cuda_flags):
|
40 |
+
return cpp_extension.load(
|
41 |
+
name=name,
|
42 |
+
sources=sources,
|
43 |
+
build_directory=buildpath,
|
44 |
+
extra_cflags=['-O3', ],
|
45 |
+
extra_cuda_cflags=['-O3',
|
46 |
+
'-gencode', 'arch=compute_70,code=sm_70',
|
47 |
+
'--use_fast_math'] + extra_cuda_flags + cc_flag,
|
48 |
+
verbose=1
|
49 |
+
)
|
50 |
+
|
51 |
+
extra_flags = []
|
52 |
+
|
53 |
+
cache_autogptq_cuda_256_sources = ["./cache_autogptq_cuda_256.cpp",
|
54 |
+
"./cache_autogptq_cuda_kernel_256.cu"]
|
55 |
+
cache_autogptq_cuda_256 = _cpp_extention_load_helper("cache_autogptq_cuda_256", cache_autogptq_cuda_256_sources, extra_flags)
|