[rollout] perf: replace AsyncOpenAI to aiohttp client in ChatCompletionScheduler#1588
Merged
vermouth1992 merged 1 commit intomainfrom May 20, 2025
Merged
[rollout] perf: replace AsyncOpenAI to aiohttp client in ChatCompletionScheduler#1588vermouth1992 merged 1 commit intomainfrom
vermouth1992 merged 1 commit intomainfrom
Conversation
wuxibin89
requested review from
PeterSH6,
hongpeng-guo,
tongyx361 and
vermouth1992
Collaborator
hongpeng-guo
left a comment
hongpeng-guo
left a comment
There was a problem hiding this comment.
LGTM, just with one small nit question.
| timeout=None, | ||
| max_retries=0 | ||
| ) | ||
| client = AsyncOpenAI(base_url=f"http://{address}/v1", api_key="token-abc123", timeout=None, max_retries=0) |
Collaborator
There was a problem hiding this comment.
It seems this line is the same as before, but the format changes. Just want to double check if the current one is lint with the pre-commit hook :)
Collaborator
Author
There was a problem hiding this comment.
Yes, it's auto format by pre-commit hook.
vermouth1992
approved these changes
May 20, 2025
Contributor
|
@wuxibin89 I found that this PR reintroduced the problem fixed in #1483 because we switched from httpx to aiohttp which has a default timeout of 5 minutes. Would you mind having a look at this error to fix it? CC @U-rara. |
6 tasks
Contributor
|
I ended up creating a PR #1702 @U-rara @wuxibin89. Please take a look |
chenjiaoAngel
added a commit
to chenjiaoAngel/verl
that referenced
this pull request
Nov 14, 2025
…onScheduler (verl-project#1588) ### Checklist Before Starting - [ ] Search for similar PR(s). ### What does this PR do? AsyncOpenAI has very severe performance issue due to httpx, replace it to aiohttp client. For train_batch_size=1024, AsyncOpenAI introduces ~25s per generation phase. ### High-Level Design > Demonstrate the high-level design if this PR is complex. ### Specific Changes > List the specific changes. ### API > Demonstrate how the API changes if any. ### Usage Example > Provide usage example(s) for easier usage. ```python # Add code snippet or script demonstrating how to use this ``` ### Test > For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluatuion results, etc. ### Additional Info. - **Issue Number**: Fixes issue # or discussion # if any. - **Training**: [Note which backend this PR will affect: FSDP, Megatron, both, or none] - **Inference**: [Note which backend this PR will affect: vLLM, SGLang, both, or none] ### Checklist Before Submitting - [ ] Read the [Contribute Guide](https://github.com/volcengine/verl?tab=readme-ov-file#contribution-guide). - [ ] Apply [pre-commit checks](https://github.com/volcengine/verl?tab=readme-ov-file#code-linting-and-formatting). - [ ] Add `[BREAKING]` to the PR title if it breaks any API. - [ ] Update the documentation about your changes in the [docs](https://github.com/volcengine/verl/tree/main/docs). - [ ] Add CI test(s) if necessary.
TimurTaepov
pushed a commit
to giorgossideris/verl
that referenced
this pull request
Dec 20, 2025
…onScheduler (verl-project#1588) ### Checklist Before Starting - [ ] Search for similar PR(s). ### What does this PR do? AsyncOpenAI has very severe performance issue due to httpx, replace it to aiohttp client. For train_batch_size=1024, AsyncOpenAI introduces ~25s per generation phase. ### High-Level Design > Demonstrate the high-level design if this PR is complex. ### Specific Changes > List the specific changes. ### API > Demonstrate how the API changes if any. ### Usage Example > Provide usage example(s) for easier usage. ```python # Add code snippet or script demonstrating how to use this ``` ### Test > For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluatuion results, etc. ### Additional Info. - **Issue Number**: Fixes issue # or discussion # if any. - **Training**: [Note which backend this PR will affect: FSDP, Megatron, both, or none] - **Inference**: [Note which backend this PR will affect: vLLM, SGLang, both, or none] ### Checklist Before Submitting - [ ] Read the [Contribute Guide](https://github.com/volcengine/verl?tab=readme-ov-file#contribution-guide). - [ ] Apply [pre-commit checks](https://github.com/volcengine/verl?tab=readme-ov-file#code-linting-and-formatting). - [ ] Add `[BREAKING]` to the PR title if it breaks any API. - [ ] Update the documentation about your changes in the [docs](https://github.com/volcengine/verl/tree/main/docs). - [ ] Add CI test(s) if necessary.
vyomakesh0728
added a commit
to vyomakesh0728/verl
that referenced
this pull request
Jan 22, 2026
…onScheduler (verl-project#1588) ### Checklist Before Starting - [ ] Search for similar PR(s). ### What does this PR do? AsyncOpenAI has very severe performance issue due to httpx, replace it to aiohttp client. For train_batch_size=1024, AsyncOpenAI introduces ~25s per generation phase. ### High-Level Design > Demonstrate the high-level design if this PR is complex. ### Specific Changes > List the specific changes. ### API > Demonstrate how the API changes if any. ### Usage Example > Provide usage example(s) for easier usage. ```python # Add code snippet or script demonstrating how to use this ``` ### Test > For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluatuion results, etc. ### Additional Info. - **Issue Number**: Fixes issue # or discussion # if any. - **Training**: [Note which backend this PR will affect: FSDP, Megatron, both, or none] - **Inference**: [Note which backend this PR will affect: vLLM, SGLang, both, or none] ### Checklist Before Submitting - [ ] Read the [Contribute Guide](https://github.com/volcengine/verl?tab=readme-ov-file#contribution-guide). - [ ] Apply [pre-commit checks](https://github.com/volcengine/verl?tab=readme-ov-file#code-linting-and-formatting). - [ ] Add `[BREAKING]` to the PR title if it breaks any API. - [ ] Update the documentation about your changes in the [docs](https://github.com/volcengine/verl/tree/main/docs). - [ ] Add CI test(s) if necessary.
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.
Checklist Before Starting
What does this PR do?
AsyncOpenAI has very severe performance issue due to httpx, replace it to aiohttp client. For train_batch_size=1024, AsyncOpenAI introduces ~25s per generation phase.
High-Level Design
Specific Changes
API
Usage Example
# Add code snippet or script demonstrating how to use thisTest
Additional Info.
Checklist Before Submitting
[BREAKING]to the PR title if it breaks any API.