-
-
Notifications
You must be signed in to change notification settings - Fork 4.3k
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
[Bugfix] Prevent crash from attempting to use a CUDA graph for a batch size that wasn't captured #7999
[Bugfix] Prevent crash from attempting to use a CUDA graph for a batch size that wasn't captured #7999
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
f840410
to
92c1aa7
Compare
Thanks @tjohnson31415 for this important fix! Might it be better to instead adjust the effective match batch size used in determining what graph sizes to capture upfront? I.e. multiply it by the max number of speculative tokens? |
@njhill My understanding is that limiting CUDA graph compilation to support That still might be a good change, but I think it can be a separate change from this bugfix PR. Even if other parts of the code better handle the batch expansion, |
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 @tjohnson31415, I agree it's good to fix this here regardless
and batch_size <= _BATCH_SIZES_TO_CAPTURE[-1] | ||
and max_decode_seq_len <= self.runner.max_seq_len_to_capture) | ||
# graphs are only captured to support up to max_num_seqs | ||
and batch_size <= _get_graph_batch_size( | ||
self.scheduler_config.max_num_seqs) and |
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.
Could we store the max as an instance field when capturing the graph in capture_model()
(i.e. batch_size_capture_list[-1]
) .. so that the check here is simpler/cheaper (it will replace both of these batch_size <=
checks).
Limiting based on max_num_seqs is just because any graphs bigger than that would never be used so no point in spending the additional capture time + memory. I don't think it would be confusing that the spec decoding config factors into this effective max batch calculation. There's anyhow a hard cap of 256, I'm not suggesting that we necessarily increase this .. i.e. that limit would still be hit if max_num_seqs was 64 and max spec tokens was 4... |
@tjohnson31415 ah looks like this may also be covered by #7894 |
didn't expect #7894 conflicts with this pr 🤣 |
Ah, yep, and #7894 already includes the refactor to store the max batch size. 🚀 |
@tjohnson31415 if batch expansion means that the effective batch size can actually be |
The interaction of batch expansion in speculative decoding, with CUDA graph capture, and setting
--max-num-seqs
less than 256 can result in a crash due to a KeyError when the server looks for a CUDA graph batch size that is not captured.The occurence of the crash comes from a few factors:
capture_model
supporting batch sizes up tomax_num_seqs
or 256 (_BATCH_SIZES_TO_CAPTURE[-1]
) (whichever is smaller) REFmax_num_seqs
is user configurable and is intended to limit the maximum batch sizemax_num_seqs
The fix proposed in this PR is to add an additional check in
_use_captured_graph()
to not use a graph if the internal batch size is greater thanget_graph_batch_size(max_num_seqs)
so that we don't try to use a graph for a batch size that wasn't captured.Example stacktrace:
FIX #6306
FIX #7907
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.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!