perf: Qwen image optimize.#1230
Open
shan-chen-feng wants to merge 2 commits intojd-opensource:mainfrom
Open
Conversation
shan-chen-feng
requested review from
DongheJin,
JimHsiung,
RobbieLeung,
XuZhang99,
liutongxuan,
walsonyang and
yq33victor
as code owners
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a communication and computation overlap mechanism for sequence parallelism in the DiT model. It adds a new QwenDoubleStreamAttnProcessorCMO2_0 implementation, updates the transformer block to support this mode via a new global flag, and refactors positional embedding handling. The review feedback highlights several style improvements, including replacing auto with explicit types, using the torch:: namespace, marking implementation classes as final, and fixing typos in parameter annotations.
| const torch::Tensor& encoder_hidden_states_mask = torch::Tensor(), | ||
| const torch::Tensor& attention_mask = torch::Tensor(), | ||
| const std::tuple<at::Tensor, at::Tensor>& image_rotary_emb = {}) { | ||
| const std::tuple<at::Tensor, at::Tensor>& image_rotary_emb = {}) = 0; |
Contributor
There was a problem hiding this comment.
Use the torch:: namespace instead of at:: for tensor declarations.
Suggested change
| const std::tuple<at::Tensor, at::Tensor>& image_rotary_emb = {}) = 0; | |
| const std::tuple<torch::Tensor, torch::Tensor>& image_rotary_emb = {}) = 0; |
References
- Use torch:: namespace instead of at:: or c10:: wherever possible. Prefer the highest-level PyTorch C++ API. (link)
Comment on lines
+1565
to
+1566
| /*pre_tockens=*/65535, | ||
| /*next_tockens=*/65535); |
Contributor
There was a problem hiding this comment.
Correct the typos in the parameter annotations: tockens should be tokens.
Suggested change
| /*pre_tockens=*/65535, | |
| /*next_tockens=*/65535); | |
| /*pre_tokens=*/65535, | |
| /*next_tokens=*/65535); |
References
- Annotate constant arguments with a comment indicating the parameter name when calling functions or constructors. (link)
shan-chen-feng
force-pushed
the
qwen_image_optimize
branch
from
1ae65d3 to
bd0a8b0
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
No description provided.