Skip to content

update ccl.py for error type #24

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.

Sign up for GitHub

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

Merged
delock merged 4 commits into from
Oct 30, 2023
Merged

update ccl.py for error type #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3589cad
Remove PP Grad Tail Check (#2538)
Quentin-Anthony Oct 26, 2023
764f5b0
Added __HIP_PLATFORM_AMD__=1 (#4570)
rraminen Oct 26, 2023
8f168c2
fix multiple definition while building evoformer (#4556)
fecet Oct 26, 2023
67aaf05
Update ccl.py
Liangliang-Ma Oct 27, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 ...speed4science/evoformer_attn/attention.cu → ...ed4science/evoformer_attn/attention_cu.cu
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion deepspeed/comm/ccl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,7 @@ def get_all_ranks_from_group(self, group):
while True:
results.append(super(CCLBackend, self).get_global_rank(group, rank))
rank += 1
except ValueError:
except (ValueError, RuntimeError):
pass
if tuple(results) not in self.groups:
self._new_group(results, group)
Expand Down
2 changes: 1 addition & 1 deletion deepspeed/runtime/pipe/engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -988,7 +988,7 @@ def _exec_send_grads(self, buffer_id):
if isinstance(inputs, tuple):
first_input = inputs[0]
assert all([torch.is_tensor(elt) for elt in inputs[1:]])
inputs_grad_tail = [elt.grad for elt in inputs[1:] if elt.grad is not None]
inputs_grad_tail = [elt.grad for elt in inputs[1:]]
elif torch.is_tensor(inputs):
first_input = inputs
inputs_grad_tail = []
Expand Down
3 changes: 3 additions & 0 deletions op_builder/builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -486,6 +486,9 @@ def jit_load(self, verbose=True):
cxx_args.append("-DBF16_AVAILABLE")
nvcc_args.append("-DBF16_AVAILABLE")

if self.is_rocm_pytorch():
cxx_args.append("-D__HIP_PLATFORM_AMD__=1")

op_module = load(name=self.name,
sources=self.strip_empty_entries(sources),
extra_include_paths=self.strip_empty_entries(extra_include_paths),
Expand Down
2 changes: 1 addition & 1 deletion op_builder/evoformer_attn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ def extra_ldflags(self):

def sources(self):
src_dir = 'csrc/deepspeed4science/evoformer_attn'
return [f'{src_dir}/attention.cpp', f'{src_dir}/attention_back.cu', f'{src_dir}/attention.cu']
return [f'{src_dir}/attention.cpp', f'{src_dir}/attention_back.cu', f'{src_dir}/attention_cu.cu']

def nvcc_args(self):
args = super().nvcc_args()
Expand Down