-
Notifications
You must be signed in to change notification settings - Fork 284
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add DeepSpeed easyblock #3450
base: develop
Are you sure you want to change the base?
Add DeepSpeed easyblock #3450
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,61 @@ | ||
from easybuild.easyblocks.generic.pythonpackage import PythonPackage | ||
from easybuild.tools.build_log import EasyBuildError | ||
from easybuild.tools.config import build_option | ||
import easybuild.tools.environment as env | ||
|
||
|
||
class EB_DeepSpeed(PythonPackage): | ||
"""Custom easyblock for DeepSpeed""" | ||
|
||
@staticmethod | ||
def extra_options(): | ||
"""Change some defaults for easyconfig parameters.""" | ||
extra_vars = PythonPackage.extra_options() | ||
extra_vars['use_pip'][0] = True | ||
extra_vars['download_dep_fail'][0] = True | ||
extra_vars['sanity_pip_check'][0] = True | ||
return extra_vars | ||
|
||
def __init__(self, *args, **kwargs): | ||
"""Initialize DeepSpeed easyblock.""" | ||
super().__init__(*args, **kwargs) | ||
|
||
dep_names = set(dep['name'] for dep in self.cfg.dependencies()) | ||
|
||
# require that PyTorch is listed as dependency | ||
if 'PyTorch' not in dep_names: | ||
raise EasyBuildError('PyTorch not found as a dependency') | ||
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.10, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.11, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, modules-3.2.10, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, modules-3.2.10, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, modules-tcl-1.147, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, modules-tcl-1.147, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, modules-4.1.4, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.6, modules-4.1.4, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.7, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.8, Lmod-8.1.14, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-6.6.3, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-6.6.3, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-7.8.22, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-7.8.22, Tcl)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-8.1.14, Lua)
Check failure on line 27 in easybuild/easyblocks/d/deepspeed.py GitHub Actions / build (3.9, Lmod-8.1.14, Tcl)
|
||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think we shouldn't error inside the init method, maybe move this to the build steps instead? The test suite doesn't like this at all. |
||
|
||
# enable building with GPU support if CUDA is included as dependency | ||
if 'CUDA' in dep_names: | ||
self.with_cuda = True | ||
else: | ||
self.with_cuda = False | ||
|
||
@property | ||
def cuda_compute_capabilities(self): | ||
return self.cfg['cuda_compute_capabilities'] or build_option('cuda_compute_capabilities') | ||
|
||
def configure_step(self): | ||
"""Set up DeepSpeed config""" | ||
|
||
if self.with_cuda: | ||
# https://github.com/microsoft/DeepSpeed/issues/3358 | ||
env.setvar('NVCC_PREPEND_FLAGS', '--forward-unknown-opts') | ||
|
||
if self.cuda_compute_capabilities: | ||
# specify CUDA compute capabilities via $TORCH_CUDA_ARCH_LIST | ||
env.setvar('TORCH_CUDA_ARCH_LIST', ';'.join(self.cuda_compute_capabilities)) | ||
|
||
# By default prebuild all opts with a few exceptions | ||
# http://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops | ||
# > DeepSpeed will only install any ops that are compatible with your machine | ||
env.setvar('DS_BUILD_OPTS', '1') | ||
|
||
# These have bothersome dependencies | ||
env.setvar('DS_BUILD_SPARSE_ATTN', '0') # requires PyTorch<2.0, triton==1.0.0 | ||
env.setvar('DS_BUILD_EVOFORMER_ATTN', '0') # requires PyTorch<2.0, triton==1.0.0 | ||
env.setvar('DS_BUILD_CUTLASS_OPS', '0') # requires dskernels | ||
env.setvar('DS_BUILD_RAGGED_DEVICE_OPS', '0') # requires dskernels | ||
|
||
super().configure_step() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
please include comment block on + you as the author