[None][doc] Add doc for multimodal feature support matrix #6619
Conversation
📝 WalkthroughWalkthroughA new documentation file was introduced, presenting a feature support matrix for multimodal models in the PyTorch backend. The matrix lists nine models and their support status for four specific features, using a tabular format to indicate whether each model supports each feature. Changes
Sequence Diagram(s)Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Note 🔌 MCP (Model Context Protocol) integration is now available in Early Access!Pro users can now connect to remote MCP servers under the Integrations page to get reviews and chat conversations that understand additional development context. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ 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)
✨ 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 comments)
Other keywords and placeholders
Documentation and Community
|
chang-l
requested review from
yechank-nvidia,
brb-nv,
amukkara,
symphonylyh and
rakib-hasan
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (3)
docs/source/reference/multimodal-feature-support-matrix.md (3)
3-4: Clarify column names & abbreviations for self-contained readability“CUDA Graph” is usually referred to in plural form (“CUDA Graphs”) throughout the TensorRT-LLM docs, and “IFB w/ SharedTensor” is an internal shorthand that external readers may not understand. Consider renaming for consistency and adding an inline footnote or parenthetical expansion (e.g., “Incremental Forward Buffer (IFB) w/
SharedTensor”) to avoid forcing readers to hunt for definitions.-| Model | CUDA Graph | IFB w/ SharedTensor | KV Cache Reuse | Chunked Prefill | +| Model | CUDA Graphs | IFB (Incremental Forward Buffer) w/ SharedTensor | KV Cache Reuse | Chunked Prefill |
5-13: Add “Last-verified” disclaimer to reduce future staleness riskSupport status can drift quickly as back-ends evolve. Adding a lightweight “Last verified” note (date + TensorRT-LLM commit) below the table makes it clear when the matrix was accurate and reminds maintainers to update it.
| Qwen2.5-VL | Yes | Yes | Yes | No | | +> **Last verified:** 2025-08-xx against commit `<short-sha>`. Please update after any multimodal feature changes.
5-13: Alphabetise model list for easier scanningOrdering models alphabetically (or by release date) improves discoverability. At the moment “Gemma 3” appears before “HyperCLOVA” but “Mistral” is after “Llama 4”. Consider sorting or documenting the chosen ordering scheme.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/reference/multimodal-feature-support-matrix.md(1 hunks)
🧰 Additional context used
🧠 Learnings (2)
📓 Common learnings
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
📚 Learning: in tensorrt-llm's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()...
Learnt from: yechank-nvidia
PR: NVIDIA/TensorRT-LLM#6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()` is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call `strip_for_generation()` to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
Applied to files:
docs/source/reference/multimodal-feature-support-matrix.md
⏰ 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
chang-l
requested review from
a team,
kaiyux and
Shixiaowei02
and removed request for
a team
chang-l
force-pushed
the
add_mm_feature_doc
branch
from
46c0f7c to
26eaea8
Compare
chang-l
changed the title
chang-l
force-pushed
the
add_mm_feature_doc
branch
from
26eaea8 to
8460f55
Compare
|
@chang-l Does this PR need to be cherry-picked into release/1.0 branch? |
|
/bot run --stage-list "A10-Build-docs" |
|
PR_Github #14497 [ run ] triggered by Bot |
|
PR_Github #14497 [ run ] completed with state |
nv-guomingz
force-pushed
the
add_mm_feature_doc
branch
from
1a9e6e1 to
0ff657d
Compare
chang-l
force-pushed
the
add_mm_feature_doc
branch
from
0ff657d to
376f26f
Compare
nv-guomingz
force-pushed
the
add_mm_feature_doc
branch
from
376f26f to
314c5e5
Compare
|
/bot skip --comment "docs only" |
|
PR_Github #14556 [ skip ] triggered by Bot |
chang-l
force-pushed
the
add_mm_feature_doc
branch
3 times, most recently
from
ad1fbb3 to
5307956
Compare
|
PR_Github #14556 [ skip ] completed with state |
Signed-off-by: Chang Liu (Enterprise Products) [email protected] Signed-off-by: Chang Liu <[email protected]>
Signed-off-by: Chang Liu (Enterprise Products) [email protected] Signed-off-by: Chang Liu <[email protected]>
Signed-off-by: Chang Liu (Enterprise Products) [email protected] Signed-off-by: Chang Liu <[email protected]>
Signed-off-by: Chang Liu (Enterprise Products) [email protected] Signed-off-by: Chang Liu <[email protected]>
nv-guomingz
force-pushed
the
add_mm_feature_doc
branch
from
5307956 to
da000d3
Compare
|
/bot skip --comment "docs only" |
|
PR_Github #14565 [ skip ] triggered by Bot |
|
PR_Github #14565 [ skip ] completed with state |
Signed-off-by: Chang Liu <[email protected]>
) Signed-off-by: Chang Liu <[email protected]>
Summary by CodeRabbit
Description
Test Coverage
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.