[nvbugs/5401156][fix] Avoid import all models when import trtllm._common #6266
Conversation
📝 Walkthrough""" WalkthroughThe changes update references to the Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Suggested reviewers
Poem
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 (5)
💤 Files with no reviewable changes (1)
✅ Files skipped from review due to trivial changes (2)
🚧 Files skipped from review as they are similar to previous changes (2)
⏰ 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
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
|
/bot run --stage-list "H100_PCIe-TensorRT-Post-Merge-5" |
![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)
tensorrt_llm/llmapi/llm_args.py (1)
26-28: Tighten the static typing ofcheckpoint_loaderThe field is currently typed as
Optional[object]while the JSON schema hints
atBaseCheckpointLoader. Improve IDE / mypy support by importing the class
only during type-checking and using a forward-ref in the field:if TYPE_CHECKING: from tensorrt_llm._torch.pyexecutor.config import PyTorchConfig + from tensorrt_llm._torch.models.checkpoints import BaseCheckpointLoader @@ - checkpoint_loader: Optional[object] = Field( + checkpoint_loader: Optional["BaseCheckpointLoader"] = Field( default=None, description="The checkpoint loader to use for this LLM instance.",No runtime cost (import guarded by
TYPE_CHECKING) and callers gain proper
type information.Also applies to: 1908-1913
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/_torch/__init__.py(1 hunks)tensorrt_llm/llmapi/llm_args.py(1 hunks)tests/unittest/api_stability/references/llm.yaml(1 hunks)
⏰ 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 (1)
tests/unittest/api_stability/references/llm.yaml (1)
70-71: Updated annotation aligns with the relocated classThe YAML reference now points at
tensorrt_llm._torch.models.checkpoints.BaseCheckpointLoader, matching the new module layout.
Looks good.
|
PR_Github #12605 [ run ] triggered by Bot |
|
PR_Github #12605 [ run ] completed with state |
|
/bot run |
|
PR_Github #12631 [ run ] triggered by Bot |
|
PR_Github #12631 [ run ] completed with state |
chang-l
force-pushed
the
fix-nvbug-5401156
branch
from
92605c9 to
ae034c1
Compare
|
/bot run |
|
PR_Github #12727 [ run ] triggered by Bot |
|
PR_Github #12727 [ run ] completed with state |
|
/bot run |
|
PR_Github #12741 [ run ] triggered by Bot |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tensorrt_llm/__init__.py (1)
45-45: E402 ‒ import not at top of file
BaseCheckpointLoaderis imported after executable statements (_add_trt_llm_dll_directory()and several imports). Ruff flags this (E402) and it slightly hurts startup-time readability.-from ._torch.models.checkpoints import BaseCheckpointLoader +from ._torch.models.checkpoints import BaseCheckpointLoader # noqa: E402or move the whole
_torch/package-internal import block above the first runtime call.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/__init__.py(2 hunks)
🧰 Additional context used
🪛 Ruff (0.12.2)
tensorrt_llm/__init__.py
45-45: Module level import not at top of file
(E402)
⏰ 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 (1)
tensorrt_llm/__init__.py (1)
66-70: Public-surface change verified—no stale references
- Searched for
tensorrt_llm._torch.BaseCheckpointLoaderand found no imports or references.- All internal code continues to import from
tensorrt_llm._torch.models.checkpoints.BaseCheckpointLoader, which remains unchanged.- The new alias
tensorrt_llm.BaseCheckpointLoaderis additive and introduces no breakage.
|
PR_Github #12741 [ run ] completed with state |
|
/bot run |
|
PR_Github #12746 [ run ] triggered by Bot |
|
PR_Github #12746 [ run ] completed with state |
|
/bot run |
|
PR_Github #12753 [ run ] triggered by Bot |
chang-l
force-pushed
the
fix-nvbug-5401156
branch
from
2d4c553 to
1e9ebe1
Compare
|
/bot run |
ZhanruiSunCh
force-pushed
the
fix-nvbug-5401156
branch
from
6ff333f to
a1de456
Compare
|
/bot run |
|
PR_Github #13027 [ run ] triggered by Bot |
|
PR_Github #13027 [ run ] completed with state |
chang-l
force-pushed
the
fix-nvbug-5401156
branch
from
a1de456 to
ec67d70
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #13058 [ run ] triggered by Bot |
|
PR_Github #13058 [ run ] completed with state |
chang-l
force-pushed
the
fix-nvbug-5401156
branch
from
ec67d70 to
dba7d8a
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #13081 [ run ] triggered by Bot |
|
PR_Github #13081 [ run ] completed with state |
|
/bot run |
|
PR_Github #13115 [ run ] triggered by Bot |
|
PR_Github #13115 [ run ] completed with state |
|
/bot run |
|
PR_Github #13118 [ run ] triggered by Bot |
|
PR_Github #13118 [ run ] completed with state |
…mon (NVIDIA#6266) Signed-off-by: Shreyas Misra <[email protected]>
…mon (NVIDIA#6266) Signed-off-by: Ransiki Zhang <[email protected]>
…mon (NVIDIA#6266) Signed-off-by: Lanyu Liao <[email protected]>
This is to fix the import error in post-merge:
[https://nvbugs/5401156][fix] Avoid import all models when import trtllm._common
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.