Skip to content

Commit b0a8bc9

Browse files
PaliCfacebook-github-bot
authored andcommitted
Update README.md (#145)
Summary: quick readme patch because adding dynamic loading broke compatibility with pytorch 1.12. Pull Request resolved: #145 Reviewed By: anirbanr-fb-r2p Differential Revision: D39107047 Pulled By: PaliC fbshipit-source-id: 5976fc1d2769428020ab6f4086a4bb478380e82e
1 parent 6621626 commit b0a8bc9

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33

44
# \[experimental\] MultiPy
55

6-
> :warning: **This is project is still a prototype.** Only Linux x86 is supported, and the API may change without warning. Furthermore, please **USE PYTORCH RELEASE 1.12** when using `multipy::runtime`!
6+
> :warning: **This is project is still a prototype.** Only Linux x86 is supported, and the API may change without warning. Furthermore, please **USE PYTORCH NIGHTLY** when using `multipy::runtime`!
77
88
`MultiPy` (formerly `torch::deploy` and `torch.package`) is a system that allows you to run multi-threaded python code in C++. It offers `multipy.package` (formerly `torch.package`) in order to package code into a mostly hermetic format to deliver to `multipy::runtime` (formerly `torch::deploy`) which is a runtime which takes packaged
99
code and runs it using multiple embedded Python interpreters in a C++ process without a shared global interpreter lock (GIL). For more information on how `MultiPy` works

0 commit comments

Comments
 (0)