Skip to content
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

Jump to bottom

[bugfix][distributed] do not error if two processes do not agree on p2p capability #5612

Merged
merged 2 commits into from
Jun 18, 2024
Merged

[bugfix][distributed] do not error if two processes do not agree on p2p capability #5612

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6b42638
do not error if two processes do not agree
youkaichao Jun 17, 2024
8b23a06
fix race condition
youkaichao Jun 17, 2024
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
10 changes: 8 additions & 2 deletions vllm/distributed/device_communicators/custom_all_reduce_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,7 @@ def consumer(batch_tgt: Sequence[int],
if open_success:
# modify the memory
lib.cudaMemset(pointer, 2, 1024)
lib.cudaDeviceSynchronize()
# use two queues to simulate barrier
producer_queue.get()
consumer_queue.put(0)
Expand Down Expand Up @@ -142,8 +143,13 @@ def can_actually_p2p(
for src, tgt in zip(batch_src, batch_tgt):
a = result_queue.get()
b = result_queue.get()
assert a == b
result.append(a)
if a != b:
logger.warning(
"Two processes do not agree on the P2P access"
" status on %d -> %d, treat as disabled.", src, tgt)
result.append(False)
else:
result.append(a)
return result


Expand Down
Loading