wassname/vllm
1
0 Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-10-02 12:50:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

custom allreduce + torch.compile (#10121)

Browse Source 
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
Sage Mooreandyoukaichao authored and GitHub committed 2024-11-25 22:00:16 -08:00
1 parent 519e8e4182
commit 9a88f89799
6 files changed
+62 -104
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/source/getting_started/debugging.rst
-1
View File
@@ -86,7 +86,6 @@ If GPU/CPU communication cannot be established, you can use the following Python
from vllm.distributed.device_communicators.pynccl import PyNcclCommunicator
pynccl = PyNcclCommunicator(group=gloo_group, device=local_rank)
pynccl.disabled = False
s = torch.cuda.Stream()
with torch.cuda.stream(s):