[TRTLLM-5252][fix] Propagate mapping to intermediate layers #6611
Conversation
📝 WalkthroughWalkthroughThe updates introduce the Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (3)
✅ Files skipped from review due to trivial changes (1)
🚧 Files skipped from review as they are similar to previous changes (1)
🧰 Additional context used📓 Path-based instructions (2)**/*.py📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
**/*.{cpp,h,cu,py}📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
🧠 Learnings (2)📓 Common learnings📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...Applied to files:
⏰ 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)
🔇 Additional comments (5)
✨ 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
|
2ez4bz
force-pushed
the
dev-mistral3-projector-tp
branch
2 times, most recently
from
db267e3 to
2a96ae1
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
examples/llm-api/quickstart_advanced.py (1)
153-155: Consider maintaining configurability forfree_gpu_memory_fraction.The change hardcodes
free_gpu_memory_fractionto 0.5 and removes the ability to configure it via the--kv_cache_fractionargument. Since this is an example script demonstrating advanced usage, users might expect to experiment with different memory fractions.Consider using a fallback approach to maintain flexibility:
- # free_gpu_memory_fraction=args.kv_cache_fraction, - free_gpu_memory_fraction=0.5, + free_gpu_memory_fraction=args.kv_cache_fraction if args.kv_cache_fraction is not None else 0.5,The addition of
max_tokens=10_000is a reasonable default that provides explicit token limiting for the KV cache.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
examples/llm-api/quickstart_advanced.py(1 hunks)tensorrt_llm/_torch/models/modeling_mistral.py(2 hunks)tests/integration/test_lists/test-db/l0_dgx_h100.yml(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: The code developed for TensorRT-LLM should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile = ...).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL = ...).
Python constants should use upper snake_case (e.g., MY_CONSTANT = ...).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a file, prefer docstrings over comments in Python.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for classes and functions in Python, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the docstring for the class.
Avoid using reflection in Python when functionality can be easily achieved without it.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.
Files:
examples/llm-api/quickstart_advanced.pytensorrt_llm/_torch/models/modeling_mistral.py
**/*.{cpp,h,hpp,cc,cxx,cu,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.
Files:
examples/llm-api/quickstart_advanced.pytensorrt_llm/_torch/models/modeling_mistral.py
🧠 Learnings (4)
📓 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.
Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Learnt from: amitz-nv
PR: NVIDIA/TensorRT-LLM#5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.402Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks `is_adapter_in_cpu_cache()` and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
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.
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h100.yml
📚 Learning: applies to **/*.py : the code developed for tensorrt-llm should conform to python 3.8+....
Learnt from: CR
PR: NVIDIA/TensorRT-LLM#0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-08-04T02:12:17.582Z
Learning: Applies to **/*.py : The code developed for TensorRT-LLM should conform to Python 3.8+.
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h100.yml
📚 Learning: in tensorrt-llm, examples directory can have different dependency versions than the root requirement...
Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h100.yml
⏰ 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
🔇 Additional comments (2)
tests/integration/test_lists/test-db/l0_dgx_h100.yml (1)
54-54: Appropriate test exclusion for ongoing tensor parallelism changes.The exclusion of
unittest/_torch/modeling/test_modeling_pixtral.py::test_tensor_parallelismaligns with the PR's focus on propagating mapping to intermediate layers, which likely affects tensor parallelism behavior. The exclusion conditions are appropriately specific to prevent broader test disruption.tensorrt_llm/_torch/models/modeling_mistral.py (1)
478-478: LGTM: Mapping parameter properly propagated to patch merger.The addition of
mapping=model_config.mappingto themerging_layerLinear constructor correctly propagates the tensor parallel mapping configuration to this intermediate layer, aligning with the PR objectives.
2ez4bz
force-pushed
the
dev-mistral3-projector-tp
branch
from
2a96ae1 to
11d2341
Compare
|
/bot run |
|
PR_Github #14043 [ run ] triggered by Bot |
|
PR_Github #14043 [ run ] completed with state |
|
/bot run --reuse-test |
|
PR_Github #14068 [ run ] triggered by Bot |
|
PR_Github #14068 [ run ] completed with state |
|
/bot run --only-multi-gpu-test --extra-stage "DGX_H100-4_GPUs-Triton-Post-Merge-1, DGX_H200-8_GPUs-PyTorch-Post-Merge-1, DGX_H200-4_GPUs-PyTorch-Post-Merge-1, DGX_H200-4_GPUs-TensorRT-Post-Merge-1, DGX_H200-4_GPUs-TensorRT-Post-Merge-2, DGX_H200-4_GPUs-TensorRT-Post-Merge-3" |
|
PR_Github #14176 [ run ] triggered by Bot |
|
PR_Github #14176 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-mistral3-projector-tp
branch
from
11d2341 to
6e2a387
Compare
|
/bot run |
|
PR_Github #14236 [ run ] triggered by Bot |
|
PR_Github #14236 [ run ] completed with state |
|
/bot run --reuse-test |
|
PR_Github #14317 [ run ] triggered by Bot |
|
PR_Github #14317 [ run ] completed with state |
|
/bot run --reuse-test |
|
PR_Github #14372 [ run ] triggered by Bot |
|
PR_Github #14372 [ run ] completed with state |
|
/bot run --reuse-test |
|
PR_Github #14379 [ run ] triggered by Bot |
|
PR_Github #14379 [ run ] completed with state |
|
/bot run --reuse-test |
|
PR_Github #14493 [ run ] triggered by Bot |
|
PR_Github #14493 [ run ] completed with state |
Signed-off-by: William Zhang <[email protected]>
2ez4bz
force-pushed
the
dev-mistral3-projector-tp
branch
from
6e2a387 to
a3406b6
Compare
|
/bot run |
|
PR_Github #14508 [ run ] triggered by Bot |
|
PR_Github #14508 [ run ] completed with state |
|
/bot run --reuse-test |
|
PR_Github #14539 [ run ] triggered by Bot |
|
PR_Github #14539 [ run ] completed with state |
|
|
) This commit propagates the mapping to intermediate layers to enable tensor parallelism (amongst other things) in them. It also fixes issues with a unit test for TP for pixtral, and adds it to a test list. Signed-off-by: William Zhang <[email protected]>
) This commit propagates the mapping to intermediate layers to enable tensor parallelism (amongst other things) in them. It also fixes issues with a unit test for TP for pixtral, and adds it to a test list. Signed-off-by: William Zhang <[email protected]>
…6765) This commit propagates the mapping to intermediate layers to enable tensor parallelism (amongst other things) in them. It also fixes issues with a unit test for TP for pixtral, and adds it to a test list. Signed-off-by: William Zhang <[email protected]>
[TRTLLM-5252][fix] Propagate mapping to intermediate layers
Description
This PR percolates the
model_config.mappingdown to intermediate layers such as theMistral3MultiModalProjectorand its constituent layers.Separately, it also adds a unit test checking the tensor parallel implementation of the pixtral vision model.
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.
Summary by CodeRabbit