-
-
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
[Bugfix] Fix KeyError: 1 When Using LoRA adapters #5164
Conversation
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.
Lgtm, thanks!
@BlackBird-Coding are you planning to finish this PR with the failing stuff? or is it just flaky tests? |
It just needs lint to be fixed |
I've been working on this code and have fixed all the lint errors, but I'm still seeing a failure in the 'AMD: Prefix Caching Test'. I'm not quite sure what the issue might be |
@BlackBird-Coding some of the CI errors are unrelated to this PR (the CI is flaky), but we definitely need lint check to pass. |
@Yard1 Thanks for the heads up about the failing lint check. I've resolved the linting issues and all checks are passing now, except for some unrelated CI flakiness as you mentioned. |
@BlackBird-Coding can you merge master into your branch, that should fix the speculative decoding CI |
@Yard1 Now all check have passed, I truly appreciate your expertise and willingness to help. |
* upstream/main: (126 commits) [Bugfix][Frontend] Cleanup "fix chat logprobs" (vllm-project#5026) [Bugfix] OpenAI entrypoint limits logprobs while ignoring server defined --max-logprobs (vllm-project#5312) [Misc] Various simplifications and typing fixes (vllm-project#5368) [ci] Fix Buildkite agent path (vllm-project#5392) [Doc] Add documentation for FP8 W8A8 (vllm-project#5388) Bump version to v0.5.0 (vllm-project#5384) [Docs] Alphabetically sort sponsors (vllm-project#5386) [Docs] Add Docs on Limitations of VLM Support (vllm-project#5383) [ci] Mount buildkite agent on Docker container to upload benchmark results (vllm-project#5330) [ci] Use small_cpu_queue for doc build (vllm-project#5331) [Bugfix] Fix LLaVA-NeXT (vllm-project#5380) [Feature][Frontend]: Continued `stream_options` implementation also in CompletionRequest (vllm-project#5319) [Model] Initial support for LLaVA-NeXT (vllm-project#4199) [Misc] Improve error message when LoRA parsing fails (vllm-project#5194) [misc][typo] fix typo (vllm-project#5372) [Frontend][Misc] Enforce Pixel Values as Input Type for VLMs in API Server (vllm-project#5374) [Misc] Update to comply with the new `compressed-tensors` config (vllm-project#5350) [Bugfix] Fix KeyError: 1 When Using LoRA adapters (vllm-project#5164) [Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (vllm-project#5047) [mis][ci/test] fix flaky test in test_sharded_state_loader.py (vllm-project#5361) ...
FIX #5113
During batch inference, when using LoRA adapters, the process crashes due to attempting to remove a LoRA adapter that has already been removed.
To address this problem, I have added a condition to ensure that the LoRA adapter is only removed if it exists in the
curr_loras
list:By checking if
seq_group.lora_int_id
is present incurr_loras
before attempting to remove it, we prevent the crash that occurs when trying to remove a LoRA adapter that has already been removed.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!