Skip to content

Conversation

Potabk
Copy link
Collaborator

@Potabk Potabk commented Sep 22, 2025

What this PR does / why we need it?

This pr bump vllm commit hash to vllm-project/vllm@5aeb925
fix issues:

  1. [V0 Deprecation] Remove V0 sampling metadata vllm#25345 has remove v0 metadata
  2. [V0 Deprecation] Remove V0 Sequence class & Sampler vllm#25332
  3. [V0 Deprecation] Remove async_output_proc, preemption mode, delay factor vllm#25334
  4. Generate _ModelInfo properties file when loading to improve loading speed vllm#23558, note that this vllm commit update the model register logic, which will check all the model registered have the vllm.model_executor.models path , which breaks our custom registration of the deepseek_v3 model (it doesn't exist in the vllm model path). so I move deepseek_v3 model registy to deepseek_v2 to solve temporary

Does this PR introduce any user-facing change?

How was this patch tested?

Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Copy link

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

@github-actions github-actions bot added documentation Improvements or additions to documentation module:tests module:ops module:core labels Sep 22, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the vLLM dependency to a newer commit. The changes primarily involve adapting to API modifications in vLLM, such as the removal of SamplingMetadata from several function signatures and changes in the sampler module. While most of the changes are correct adaptations, I've found several critical issues where compute_logits method signatures in various models were not fully updated. This will lead to TypeError exceptions at runtime. I have provided suggestions to fix these issues.

Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
self,
lm_head: VocabParallelEmbedding,
hidden_states: torch.Tensor,
# keep this for version compatibility
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it's better to add a todo: delete arg sampling_metadata when dropping v0.10.2

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ok, let's wait for ci passed, and I'll have a push

Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
@Potabk Potabk added ready read for review ready-for-test start test by label for PR labels Sep 22, 2025
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
self.lm_head = PPMissingLayer()
self.logits_processor = LogitsProcessor(config.vocab_size)
self.sampler = get_sampler()
self.sampler = Sampler()
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ditto

@wangxiyuan wangxiyuan merged commit 02f89d1 into vllm-project:main Sep 22, 2025
19 checks passed
@Potabk Potabk deleted the fix branch September 23, 2025 01:00
@Yikun Yikun added vllm-break and removed ready-for-test start test by label for PR labels Sep 26, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation module:core module:ops module:tests ready read for review vllm-break
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants