[MP][Bugfix] fix free error when memory_objs is empty#2768
[MP][Bugfix] fix free error when memory_objs is empty#2768ApostaC merged 2 commits intoLMCache:devfrom
Conversation
Signed-off-by: idellzheng <idellzheng@tencent.com>
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request addresses a critical bug where the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request addresses a potential IndexError in MixedMemoryAllocator.batched_free that occurs when memory_objs is an empty list. The fix involves adding a guard clause at the beginning of the method to return early if the list is empty. This same protective check has been consistently applied to the batched_free methods in TensorMemoryAllocator and PagedTensorMemoryAllocator as well, improving robustness even though they were not susceptible to the same crash. The changes are correct and effectively resolve the bug.
maobaolong
left a comment
There was a problem hiding this comment.
LGTM. This is an obvious bug, thanks for this fix.
Signed-off-by: idellzheng <idellzheng@tencent.com>
Signed-off-by: idellzheng <idellzheng@tencent.com> Signed-off-by: Aaron Wu <aaron.wu@dell.com>
Signed-off-by: idellzheng <idellzheng@tencent.com>
Signed-off-by: idellzheng <idellzheng@tencent.com>
Signed-off-by: idellzheng <idellzheng@tencent.com>
Signed-off-by: idellzheng <idellzheng@tencent.com>
fix this error when not use
lazy_memory_allocatorin mp mode.In mp mode, if use
MixedMemoryAllocator, when trigger write to L2, will firstreserve_readL1 objects and thenfinish_read,finish_readwill callself._memory_manager.free(need_to_free), but allmem_objsis nottemp, andneed_to_allocateis empty, this will trigger this bug.