[TRTLLM-5059][feat] Enable KV-cache reuse and add E2E tests for llava-next #7349
Conversation
📝 WalkthroughWalkthroughIntroduces a preprocessing step in LLaVA-Next’s non-DISAGG forward path: after obtaining multimodal embeddings, applies find_uncached_mm_embeds to mm_embeds based on multimodal_params, then proceeds to fuse_input_embeds. Imports are updated accordingly. DISAGG path is unchanged. No public API signatures are modified. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor Caller
participant LLaVA_Next as LLaVA-Next Model
participant MM_Embed as multimodal_embedding / mm_encoder
participant Uncached as find_uncached_mm_embeds
participant Fuse as fuse_input_embeds
Caller->>LLaVA_Next: forward(input_ids, multimodal_params, ...)
alt DISAGG == false and multimodal_params present
LLaVA_Next->>MM_Embed: compute mm_embeds
MM_Embed-->>LLaVA_Next: mm_embeds
LLaVA_Next->>Uncached: find_uncached_mm_embeds(mm_embeds, multimodal_params[:num_context_requests])
Uncached-->>LLaVA_Next: filtered/transformed mm_embeds
LLaVA_Next->>Fuse: fuse_input_embeds(input_embeds, mm_embeds, ...)
Fuse-->>LLaVA_Next: fused_embeds
else DISAGG == true or no multimodal_params
LLaVA_Next->>Fuse: fuse_input_embeds(input_embeds, mm_embeds, ...)
Fuse-->>LLaVA_Next: fused_embeds
end
LLaVA_Next-->>Caller: outputs
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Suggested reviewers
✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tensorrt_llm/_torch/models/modeling_llava_next.py(2 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{cpp,cc,cxx,cu,py,h,hpp,hh,hxx,cuh}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use spaces only; no tabs; indent by 4 spaces
Files:
tensorrt_llm/_torch/models/modeling_llava_next.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent with 4 spaces; no tabs
Keep module namespace on import; import the module, not individual names; use module.symbol
Python filenames use snake_case (e.g., some_file.py)
Class names use PascalCase
Function and method names use snake_case
Local variables use snake_case; if starting with a number, prefix with k_ (e.g., k_99th_percentile)
Global variables use UPPER_SNAKE with G_ prefix (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE
Avoid shadowing variables from outer scopes
Initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with trailing docstrings
Avoid reflection when simple alternatives exist (e.g., avoid dict(**locals()) patterns)
Limit except clauses to specific exceptions; avoid bare except
When duck-typing with try/except, keep try body minimal and use else for logic
Files:
tensorrt_llm/_torch/models/modeling_llava_next.py
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tensorrt_llm/_torch/models/modeling_llava_next.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
|
/bot run |
|
PR_Github #16898 [ run ] triggered by Bot |
|
PR_Github #16898 [ run ] completed with state |
chang-l
changed the title
chang-l
changed the title
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
chang-l
force-pushed
the
enable_kvcache_reuse_llavanext
branch
from
18c74d7 to
f27d7c2
Compare
chang-l
changed the title
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
|
/bot run |
|
PR_Github #18101 [ run ] triggered by Bot |
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
|
PR_Github #18101 [ run ] completed with state |
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
|
/bot reuse-pipeline |
1 similar comment
|
/bot reuse-pipeline |
|
PR_Github #18257 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #18257 [ reuse-pipeline ] completed with state |
…-next (NVIDIA#7349) Signed-off-by: Chang Liu (Enterprise Products) <9713593+chang-l@users.noreply.github.com>
5 participants
This PR is related to #7628 and #7563, and should be kept in sync.
Summary by CodeRabbit
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.