[FFI] AudoDLPack compatible with torch stream context #18217
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Member
Author
|
ffi overhead benchmark |
This PR updates the autodlpack path to automatically update the env stream to be consistent with torch stream context. The change would help to make FFI functions to be compatible in stream based executions. We leverage torch cpp_extension load_inline to create an efficient query function, the first time loading might take more time to build the jit module and things should be fast after the torch jit module is cached.
yongwww
approved these changes
Aug 19, 2025
tqchen
added a commit
to tqchen/tvm
that referenced
this pull request
Sep 13, 2025
This PR updates the autodlpack path to automatically update the env stream to be consistent with torch stream context. The change would help to make FFI functions to be compatible in stream based executions. We leverage torch cpp_extension load_inline to create an efficient query function, the first time loading might take more time to build the jit module and things should be fast after the torch jit module is cached.
tqchen
added a commit
to tqchen/tvm
that referenced
this pull request
Sep 13, 2025
This PR updates the autodlpack path to automatically update the env stream to be consistent with torch stream context. The change would help to make FFI functions to be compatible in stream based executions. We leverage torch cpp_extension load_inline to create an efficient query function, the first time loading might take more time to build the jit module and things should be fast after the torch jit module is cached.
tqchen
added a commit
to tqchen/tvm
that referenced
this pull request
Sep 13, 2025
This PR updates the autodlpack path to automatically update the env stream to be consistent with torch stream context. The change would help to make FFI functions to be compatible in stream based executions. We leverage torch cpp_extension load_inline to create an efficient query function, the first time loading might take more time to build the jit module and things should be fast after the torch jit module is cached.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR updates the autodlpack path to automatically update the env stream to be consistent with torch stream context.
The change would help to make FFI functions to be compatible in stream based executions.
Specifically, TVMFFIEnvSetStream will be called to set the stream from the torch cuda context so the callee can query the stream via TVMFFIEnvGetCurrentStream. The stream will be recovered after the function call ends
We leverage torch cpp_extension load_inline to create an efficient stream query function so it won't slow down the call, the first time loading might take more time to build the jit module and things should be fast after the torch jit module is cached.