xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-14 15:45:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[bugfix][distributed] improve p2p capability test (#5612)

Browse Source 
[bugfix][distributed] do not error if two processes do not agree on p2p capability (#5612)
This commit is contained in:
youkaichao 2024-06-18 00:21:05 -07:00 committed by GitHub
parent 114d7270ff
commit db5ec52ad7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/distributed/device_communicators/custom_all_reduce_utils.py
View File

@ -71,6 +71,7 @@ def consumer(batch_tgt: Sequence[int],
if open_success: if open_success:
# modify the memory # modify the memory
lib.cudaMemset(pointer, 2, 1024) lib.cudaMemset(pointer, 2, 1024)
lib.cudaDeviceSynchronize()
# use two queues to simulate barrier # use two queues to simulate barrier
producer_queue.get() producer_queue.get()
consumer_queue.put(0) consumer_queue.put(0)
@ -142,8 +143,13 @@ def can_actually_p2p(
for src, tgt in zip(batch_src, batch_tgt): for src, tgt in zip(batch_src, batch_tgt):
a = result_queue.get() a = result_queue.get()
b = result_queue.get() b = result_queue.get()
assert a == b if a != b:
result.append(a) 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 return result