Main2main upgrade vllm commit to 03 19 17:00#7478
Main2main upgrade vllm commit to 03 19 17:00#7478wangxiyuan merged 10 commits intovllm-project:mainfrom
Conversation
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request updates the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Ignored Files
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. Footnotes
|
There was a problem hiding this comment.
Code Review
The pull request updates a vLLM commit hash in the docs/source/community/versioning_policy.md file, specifically changing the commit hash for the main branch's compatibility with vLLM. This is a minor documentation update. However, the pull request title and description do not adhere to the repository's defined style guide for pull request formatting. The PR title should follow the format [Branch][Module][Action] Pull Request Title, for example: [main][Doc][Misc] Upgrade vLLM commit hash in versioning policy. The PR summary should be filled out according to the template provided in the style guide, detailing what the PR does, why it's needed, if it introduces user-facing changes, and how it was tested.
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
5900db1 to
5883a61
Compare
5883a61 to
e09e5b0
Compare
af92ad1 to
04f424c
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
04f424c to
a4133d6
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
…astic_ep: Fix stateless group port races, commit de1a86b7d) refactored StatelessProcessGroup and removed the socket: socket.socket | None field. The socket ownership was moved to a new create_tcp_store() helper instead of being stored as a field on the dataclass. Fix: Removed the now-invalid socket=None keyword argument from the StatelessProcessGroup Signed-off-by: leo-pony <nengjunma@outlook.com>
…tual engine #37195) removed the virtual_engine parameter from set_forward_context(), create_forward_context(), and the ForwardContext dataclass. This broke vllm-ascend which was passing virtual_engine in kwargs and accessing forward_context.virtual_engine Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
a4133d6 to
49905e2
Compare
Signed-off-by: leo-pony <nengjunma@outlook.com>
49905e2 to
c104b7a
Compare
Signed-off-by: leo-pony <nengjunma@outlook.com>
86e1250 to
79e1a8c
Compare
Signed-off-by: leo-pony <nengjunma@outlook.com>
79e1a8c to
137395d
Compare
Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it? Upgrade vllm commit to 2026.03.19. 1.Fix socket removed from StatelessProcessGroup. Upstream vLLM PR [#36330](vllm-project/vllm#36330) ("elastic_ep: Fix stateless group port races") refactored StatelessProcessGroup and removed the socket: socket.socket | None field. The socket ownership was moved to a new create_tcp_store() helper instead of being stored as a field on the dataclass. 2.fix `virtual_engine` parameter removed from `set_forward_context(). Upstream [V0 Deprecation] Deprecate virtual engine [#37195](vllm-project/vllm#37195) ### Does this PR introduce _any_ user-facing change? NA ### How was this patch tested? NA - vLLM version: v0.17.0 - vLLM main: vllm-project/vllm@8b63257 --------- Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it? Upgrade vllm commit to 2026.03.19. 1.Fix socket removed from StatelessProcessGroup. Upstream vLLM PR [#36330](vllm-project/vllm#36330) ("elastic_ep: Fix stateless group port races") refactored StatelessProcessGroup and removed the socket: socket.socket | None field. The socket ownership was moved to a new create_tcp_store() helper instead of being stored as a field on the dataclass. 2.fix `virtual_engine` parameter removed from `set_forward_context(). Upstream [V0 Deprecation] Deprecate virtual engine [#37195](vllm-project/vllm#37195) ### Does this PR introduce _any_ user-facing change? NA ### How was this patch tested? NA - vLLM version: v0.17.0 - vLLM main: vllm-project/vllm@8b63257 --------- Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it? Upgrade vllm commit to 2026.03.19. 1.Fix socket removed from StatelessProcessGroup. Upstream vLLM PR [#36330](vllm-project/vllm#36330) ("elastic_ep: Fix stateless group port races") refactored StatelessProcessGroup and removed the socket: socket.socket | None field. The socket ownership was moved to a new create_tcp_store() helper instead of being stored as a field on the dataclass. 2.fix `virtual_engine` parameter removed from `set_forward_context(). Upstream [V0 Deprecation] Deprecate virtual engine [#37195](vllm-project/vllm#37195) ### Does this PR introduce _any_ user-facing change? NA ### How was this patch tested? NA - vLLM version: v0.17.0 - vLLM main: vllm-project/vllm@8b63257 --------- Signed-off-by: leo-pony <nengjunma@outlook.com>
What this PR does / why we need it?
Upgrade vllm commit to 2026.03.19.
1.Fix socket removed from StatelessProcessGroup. Upstream vLLM PR #36330 ("elastic_ep: Fix stateless group port races") refactored StatelessProcessGroup and removed the socket: socket.socket | None field. The socket ownership was moved to a new create_tcp_store() helper instead of being stored as a field on the dataclass.
2.fix
virtual_engineparameter removed from `set_forward_context(). Upstream [V0 Deprecation] Deprecate virtual engine #37195Does this PR introduce any user-facing change?
NA
How was this patch tested?
NA