biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[PERF] PyTorch Symmetric Memory All-Reduce (#20759)

Browse Source 
Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Ilya Markov
2025-08-22 23:39:08 +02:00
committed by GitHub
parent 0483fabc74
commit 0313cf854d
8 changed files with 283 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/design/multiprocessing.md
View File

@@ -77,7 +77,7 @@ The `multiproc_xpu_executor` forces the use of `spawn`.
There are other miscellaneous places hard-coding the use of `spawn`:
- <https://github.com/vllm-project/vllm/blob/d05f88679bedd73939251a17c3d785a354b2946c/vllm/distributed/device_communicators/custom_all_reduce_utils.py#L135>
- <https://github.com/vllm-project/vllm/blob/d05f88679bedd73939251a17c3d785a354b2946c/vllm/distributed/device_communicators/all_reduce_utils.py#L135>
- <https://github.com/vllm-project/vllm/blob/d05f88679bedd73939251a17c3d785a354b2946c/vllm/entrypoints/openai/api_server.py#L184>
Related PRs: