[TPU] TorchTPU backend integration - eager / torch.compile / tp - #14039
Open
JingyaHuang wants to merge 46 commits into
Open
JingyaHuang wants to merge 46 commits into
JingyaHuang wants to merge 46 commits into
Conversation
github-actions
Bot
added
documentation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
JingyaHuang
changed the title
JingyaHuang
marked this pull request as ready for review
September 7, 2026 16:23
…ster tpu.md; drop redundant execution_device check - Propagate the text_encoder.device-based fix (introduced for TPU CPU-offload support) from FluxPipeline/Flux2KleinPipeline/WanPipeline into their `# Copied from` copies (flux/*, flux2_klein_inpaint, visualcloze, anyflow, chronoedit, lucy_edit, skyreels_v2/*). SDXL-family copies of StableDiffusionXLPipeline.encode_prompt are intentionally left untouched; they'll be handled in a follow-up PR that fixes device placement for every pipeline component (not just text encoders). - Register docs/source/en/optimization/tpu.md in _toctree.yml (was breaking the docs build: "not present in the table of contents"). - Remove the redundant "prefer non-CPU, non-meta component" loop from DiffusionPipeline._execution_device: PR huggingface#14383 already fixed this in DiffusionPipeline.device, which _execution_device falls back to. Verified on TPU hardware that _execution_device still resolves correctly for a split-placement pipeline after the removal. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
stevhliu
reviewed
Sep 9, 2026
stevhliu
left a comment
stevhliu
left a comment
Member
There was a problem hiding this comment.
nice, thanks for adding docs!
do we need to also mention TP here or no?
| > [!TIP] | ||
| > For the best production throughput, prefer `torch.compile` via `pipe.enable_tpu_compile()`. | ||
|
|
||
| ## API reference |
Member
There was a problem hiding this comment.
the API section should gets it own separate page under API > Main classes under Parallel inference as thats the closest related topic
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
…rs into add-torchtpu-support
Contributor
Author
|
@stevhliu good catch, I just added a brief tp section in the doc. |
…add-torchtpu-support
stevhliu
approved these changes
Sep 14, 2026
stevhliu
left a comment
stevhliu
left a comment
Member
There was a problem hiding this comment.
thanks for adding! should we also add "tpu" as an option to the TensorParallelConfig docstring? i think currently it only says "cuda" and "neuron".
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
…rs into add-torchtpu-support
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
4 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.
What does this PR do?
Need the fix #14739 first.
torch.compileThis is a preparation based on TorchTPU beta before the official release.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.