[CI/Build] Expand Model Testing

[robertgshaw2-redhat]

Expand model testing by running:

• More small models (<1gb) with full fp32 bitwise correctness tests vs hf
• More medium models (~15gb) that can fit on single L4 gpu with logprob comparison vs hf

Observations:

• gemma and qwen do not have bitwise correctness at fp32 vs Hf implementations
• olmo, chatglm, and xverse cannot run in our CI
• Command-r, DeepSeek MoE, DBRX, Jais, Mixtral, Orion, Qwen2 MoE cannot run in our CI due to memory constraints

All other models are now covered.

This will protect us against various issues especially as it relates to changes touching all models

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

PR Checklist (Click to Expand)

Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Model] for adding a new model or improving an existing model. Model name should appear in the title.
• [Frontend] For changes on the vLLM frontend (e.g., OpenAI API server, LLM class, etc.)
• [Kernel] for changes affecting CUDA kernels or other compute kernels.
• [Core] for changes in the core vLLM logic (e.g., LLMEngine, AsyncLLMEngine, Scheduler, etc.)
• [Hardware][Vendor] for hardware-specific changes. Vendor name should appear in the prefix (e.g., [Hardware][AMD]).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• We adhere to Google Python style guide and Google C++ style guide.
• Pass all linter checks. Please use format.sh to format your code.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Include sufficient tests to ensure the project to stay correct and robust. This includes both unit tests and integration tests.
• Please add documentation to docs/source/ if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.

Notes for Large Changes

Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with rfc-required and might not go through the PR.

What to Expect for the Reviews

The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:

• After the PR is submitted, the PR will be assigned to a reviewer. Every reviewer will pick up the PRs based on their expertise and availability.
• After the PR is assigned, the reviewer will provide status update every 2-3 days. If the PR is not reviewed within 7 days, please feel free to ping the reviewer or the vLLM team.
• After the review, the reviewer will put an action-required label on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.
• Please respond to all comments within a reasonable time frame. If a comment isn't clear or you disagree with a suggestion, feel free to ask for clarification or discuss the suggestion.

Thank You

Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!

[simon-mo]

I think you need to change the pipeline yaml in .buildkite as well.

[mgoin]

Several of these left in are still tested in medium. Obviously this test is more strict as it is measuring float exact token match, but do we need to duplicate models like bloom, deepseek, starcoder?

[robertgshaw2-redhat]

I think you need to change the pipeline yaml in .buildkite as well.

Its already picked up since we use a --ignore strategy for model testing

[rkooo567]

QQ: how much e2e CI runtime is changed after this PR?

[robertgshaw2-redhat]

update is that im getting issues with ops.rotary_embeddings() in the float32 test in the CI but not locally

Trying to figure out why

[github-actions]

This pull request has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this pull request should remain open. Thank you!

[DarkLight1337]

Closing as we have pruned tests in #9940. Nevertheless, we can consider the models listed here for convenient local testing once we consolidate the language model tests (similar to what has been done for vision-language model tests).