Skip to content

[Core][MM] Cleanup MultiModalCache #25006

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 2 commits into from
Sep 18, 2025
Merged

[Core][MM] Cleanup MultiModalCache #25006

merged 2 commits into from
Sep 18, 2025

Conversation

lgeiger
Copy link
Contributor

@lgeiger lgeiger commented Sep 17, 2025 •
edited by github-actions bot
Loading

Purpose

  • Remove unused debug argument from MultiModalCache.get_leaf_size
  • Simplify isinstance checks in MultiModalCache.get_leaf_size
  • Simplify MultiModalCache.get_item_size

Test Plan

CI

@lgeiger
[Core][MM] Cleanup MultiModalCache
a831ef0 
- Remove unused debug argument from `get_leaf_size` - simplify
isinstance checks - simplify `get_item_size`

Signed-off-by: Lukas Geiger <[email protected]>
@mergify mergify bot added the multi-modality Related to multi-modality (#4194) label Sep 17, 2025
gemini-code-assist[bot]
gemini-code-assist bot reviewed Sep 17, 2025
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces several cleanups to the MultiModalCache class in vllm/multimodal/cache.py. The changes include removing an unused debug argument from MultiModalCache.get_leaf_size, simplifying multiple isinstance checks into a single check with a tuple of types, and replacing lambda functions in MultiModalCache.get_item_size with operator.add and a direct method reference. These refactorings improve code readability and maintainability. The changes are correct and well-implemented.

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) September 17, 2025 03:27
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Sep 17, 2025
@vllm-bot vllm-bot merged commit b982196 into vllm-project:main Sep 18, 2025
37 of 40 checks passed
@lgeiger lgeiger deleted the mm-cache branch September 18, 2025 06:39
845473182 pushed a commit to dsxsteven/vllm_splitPR that referenced this pull request Sep 18, 2025
Merge branch 'model_register' of https://github.com/dsxsteven/vllm_sp…
e38137d 
…litPR into model_register

* 'model_register' of https://github.com/dsxsteven/vllm_splitPR: (138 commits)
  Retrieve `sliding_window` from text config in Gemma3 MM (vllm-project#25085)
  [Docs] Fix API Reference (vllm-project#25140)
  [Kernel] Better inf handling for grouped topk cu (vllm-project#24886)
  [CLI] Use streaming in CLI chat and completion commands (vllm-project#23769)
  [benchmark] add peak throughput metrics and plot (vllm-project#23867)
  [Spec Decode] Efficient padded speculation (vllm-project#24539)
  [V0 Deprecation] Remove more V0 tests (vllm-project#25117)
  [EPLB] Add EPLB support for hunyuan_v1 (vllm-project#23078)
  [XPU] Whisper model support on XPU Platform (vllm-project#25123)
  Mark prompt logprobs as incompatible with prompt embeds at API level (vllm-project#25077)
  [Model] enable data parallel for InternVL vision encoder (vllm-project#23909)
  [Kernels] Overlap shared experts with combine instead of dispatch (vllm-project#24254)
  [Bugfix][Qwen3-Next] add prefixes to shared_expert in qwen3-next and mlp in qwen2moe to successfully load ignored params in quantized models (vllm-project#24960)
  [Core][MM] Cleanup `MultiModalCache` (vllm-project#25006)
  [Docs] Clean up the contributing README (vllm-project#25099)
  [MM Encoder] Apply DP ViT for Qwen3-VL model series (vllm-project#24955)
  [Kernels] Enable DeepGEMM by default (vllm-project#24462)
  [V0 Deprecation] Skip PP test (vllm-project#25128)
  [V0 Deprecation] Remove misc V0 tests (vllm-project#25118)
  [V0 Deprecation] Remove V0 Tracing & Metrics tests (vllm-project#25115)
  ...
debroy-rh pushed a commit to debroy-rh/vllm that referenced this pull request Sep 19, 2025
@lgeiger @debroy-rh
[Core][MM] Cleanup MultiModalCache (vllm-project#25006)
5f2ad2a 
Signed-off-by: Lukas Geiger <[email protected]>
FeiDaLI pushed a commit to FeiDaLI/vllm that referenced this pull request Sep 25, 2025
@lgeiger @FeiDaLI
[Core][MM] Cleanup MultiModalCache (vllm-project#25006)
1f363fa 
Signed-off-by: Lukas Geiger <[email protected]>
charlifu pushed a commit to ROCm/vllm that referenced this pull request Sep 25, 2025
@lgeiger @charlifu
[Core][MM] Cleanup MultiModalCache (vllm-project#25006)
91780fa 
Signed-off-by: Lukas Geiger <[email protected]>
Signed-off-by: charlifu <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 approved these changes

@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner

@NickLucche NickLucche Awaiting requested review from NickLucche NickLucche is a code owner

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements
Assignees
No one assigned
Labels
multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@lgeiger @DarkLight1337 @vllm-bot