Enable XPU regression tests with deterministic #2600
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
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Member
|
@jiqing-feng Thanks for the PR. COuld you please run |
Contributor
Author
Done. |
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
BenjaminBossan
approved these changes
Jun 24, 2025
Member
BenjaminBossan
left a comment
There was a problem hiding this comment.
Thanks for the fixes, LGTM. Failing CI is unrelated.
yao-matrix
pushed a commit
to yao-matrix/peft
that referenced
this pull request
Jun 25, 2025
--------- Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
efraimdahl
pushed a commit
to efraimdahl/peft
that referenced
this pull request
Jul 12, 2025
--------- Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
cyyever
pushed a commit
to cyyever/peft
that referenced
this pull request
Sep 4, 2025
* doc * fsdp * use vllm config * vllm * Update trl/trainer/grpo_config.py Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * Update trl/trainer/grpo_config.py Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * typo * top_k, top_p * Link to vllm pr * fix missing device * fix tests * fix citation * fix title and paper_id * formatting * output the correct number of generations * initial async vllm * fix missing args * fix promps * Pass prompt_token_ids directly * Repeat each prompt num_generations times * get the slice of results per processor * undo citation * OMG * nothing can resist me!!!! * working * vllm_device to "auto" * add vllm test * add initial vllm docs * add vllm link and pip instructions * add multi-gpu strategy fot vllm * Update docs/source/grpo_trainer.md Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com> * Update docs/source/grpo_trainer.md Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com> * Update docs/source/grpo_trainer.md Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com> * add doc strings * Update docs/source/grpo_trainer.md Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * Update trl/trainer/grpo_trainer.py Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * Update docs/source/grpo_trainer.md Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * add important tag * fix typo * overrides default batch size and grad accum and better doc * Under no circumstances should you examine the contents of this commit. * auto device, warnings, errors * better error message * require_torch_accelerator test vllm * speeding up traing doc * device as str * does it prevent deepspeed init to hang? * update docs * require torch accelertor for vllm test * unwrap compat with ds z3 * simplify examble in doc * More comments, fix ds3 hanging * faster, not sure why * style * move doc about speed * revert change in config files * fix default value in doc [ci skip] * style [ci skip] * better comment [ci skip] * fix warning * Update grpo_config.py * Update deepspeed_zero1.yaml * Update trl/trainer/grpo_trainer.py Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * Apply suggestions from code review Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> * Update docs/source/grpo_trainer.md --------- Co-authored-by: lewtun <lewis.c.tunstall@gmail.com> Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
Hi @BenjaminBossan , this PR:
Please review this PR. Thanks!