-
-
Notifications
You must be signed in to change notification settings - Fork 5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[V1] Make v1 more testable #9888
Conversation
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
28bee6d
to
bdc0443
Compare
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sampler changes look good to me. Can someone else take a look at the detokenizer fixes?
This pull request has merge conflicts that must be resolved before it can be |
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Turns out there were two problems:
Both should be fixed now 🤞 |
This pull request has merge conflicts that must be resolved before it can be |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @joerunde
# Small hack- implicit clean up of resources on garbage collect | ||
# TODO: this should probably be explicitly invoked when we're done with | ||
# the engine | ||
self.terminate_detokenizer() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is being reworked anyhow right now.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I was hoping as much!
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
This pull request has merge conflicts that must be resolved before it can be |
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com> Signed-off-by: Loc Huynh <jc1da.3011@gmail.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com> Signed-off-by: Sumit Dubey <sumit.dubey2@ibm.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com> Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com> Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
This PR fixes some small issues with running the v1 engine, and makes it easily testable.
Sampler
class was being patched over byunittest.mock.patch
in the v1 gpu executor, which is prone to import order bugs and persists as a side effect once the patch context is exitedThis PR fixes those issues, and adds an example test fixture that will run tests on both engines. This fixture can easily be enabled at the test module or test package level, an example is in
tests/entrypoints/llm/test_prompt_validation.py
. This will allow us to turn on tests for v1 as more functionality is added, ensuring code coverage as we go.Some public slack context: https://vllm-dev.slack.com/archives/C07QP347J4D/p1730394348692179
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:
format.sh
to format your code.docs/source/
if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.Adding or changing kernels
Each custom kernel needs a schema and one or more implementations to be registered with PyTorch.
Tensors
require meta-functions. Meta-functions should be implemented and registered in python so that dynamic dims can be handled automatically. See above documents for a description of meta-functions.torch.libary.opcheck()
to test the function registration and meta-function for any registered ops. Seetests/kernels
for examples.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:
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.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!