Compare commits

...

6 Commits

Author SHA1 Message Date
3212affd9e Set version to 0.1.6 (#23) 2025-02-05 15:18:50 +01:00
7ff40a859c write_egg_lockfile: bail out if the project does not have pyproject.toml (#22) 2025-02-05 14:55:51 +01:00
cf64113c8b Set version to 0.1.5 (#21) 2025-02-05 11:04:28 +01:00
ba4f88f5aa Make module names unique by path (#20)
So far we have been using the extension name in `build.toml` as
the module name. However, this can cause naming conflicts. For
instance, if a kernel named `moe` is loaded through `hf_kernels`,
it would be registered as the `moe` module. This would cause
subsequent imports of a module named `moe` from the Python path
to be resolved as the module loaded through `hf_kernels`.

Solve this issue by adding some unique material to the module
name (hex-encoded hash of the kernel path).
2025-02-05 10:55:02 +01:00
d61971ad46 Set version to 0.1.4 (#19) 2025-02-04 20:29:27 +01:00
d7f3831992 Support kernel cache directory with HF_KERNELS_CACHE env var (#18) 2025-02-04 20:18:43 +01:00
3 changed files with 28 additions and 4 deletions

View File

@ -1,6 +1,6 @@
[project]
name = "hf-kernels"
version = "0.1.3"
version = "0.1.6"
description = "Download cuda kernels"
authors = [
{ name = "OlivierDehaene", email = "olivier@huggingface.co" },

View File

@ -89,7 +89,12 @@ def write_egg_lockfile(cmd, basename, filename):
import logging
cwd = Path.cwd()
with open(cwd / "pyproject.toml", "rb") as f:
pyproject_path = cwd / "pyproject.toml"
if not pyproject_path.exists():
# Nothing to do if the project doesn't have pyproject.toml.
return
with open(pyproject_path, "rb") as f:
data = tomllib.load(f)
kernel_versions = data.get("tool", {}).get("kernels", {}).get("dependencies", None)

View File

@ -1,3 +1,4 @@
import ctypes
import importlib
import importlib.metadata
import inspect
@ -15,6 +16,8 @@ from packaging.version import parse
from hf_kernels.compat import tomllib
from hf_kernels.lockfile import KernelLock
CACHE_DIR: Optional[str] = os.environ.get("HF_KERNELS_CACHE", None)
def build_variant():
import torch
@ -29,6 +32,12 @@ def build_variant():
def import_from_path(module_name: str, file_path):
# We cannot use the module name as-is, after adding it to `sys.modules`,
# it would also be used for other imports. So, we make a module name that
# depends on the path for it to be unique using the hex-encoded hash of
# the path.
path_hash = "{:x}".format(ctypes.c_size_t(hash(file_path)).value)
module_name = f"{module_name}_{path_hash}"
spec = importlib.util.spec_from_file_location(module_name, file_path)
module = importlib.util.module_from_spec(spec)
sys.modules[module_name] = module
@ -43,6 +52,7 @@ def install_kernel(repo_id: str, revision: str, local_files_only: bool = False):
repo_path = snapshot_download(
repo_id,
allow_patterns=f"build/{build_variant()}/*",
cache_dir=CACHE_DIR,
revision=revision,
local_files_only=local_files_only,
)
@ -55,6 +65,7 @@ def install_kernel_all_variants(
snapshot_download(
repo_id,
allow_patterns="build/*",
cache_dir=CACHE_DIR,
revision=revision,
local_files_only=local_files_only,
)
@ -63,7 +74,11 @@ def install_kernel_all_variants(
def get_metadata(repo_id: str, revision: str, local_files_only: bool = False):
with open(
hf_hub_download(
repo_id, "build.toml", revision=revision, local_files_only=local_files_only
repo_id,
"build.toml",
cache_dir=CACHE_DIR,
revision=revision,
local_files_only=local_files_only,
),
"rb",
) as f:
@ -83,7 +98,11 @@ def load_kernel(repo_id: str):
raise ValueError(f"Kernel `{repo_id}` is not locked")
filename = hf_hub_download(
repo_id, "build.toml", local_files_only=True, revision=locked_sha
repo_id,
"build.toml",
cache_dir=CACHE_DIR,
local_files_only=True,
revision=locked_sha,
)
with open(filename, "rb") as f:
metadata = tomllib.load(f)