refactor: Unify decoder test with e2e worklfow #5239
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
/bot run |
There was a problem hiding this comment.
Pull Request Overview
This PR refactors the decoder test workflow to unify request creation and end‐to‐end integration. Key changes include:
- Replacing the legacy prepareRequests function with createLlmRequest(s) to build request objects.
- Updating the tests to call the new request creation functions and adjusting the related newRequests calls.
- Adding a check for mSeqSlot in the decoder requests creation and removing a duplicated function signature in the header.
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| cpp/tests/runtime/gptDecoderBatchedTest.cpp | Refactored test request creation with new LLM request functions and updated newRequests calls. |
| cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp | Added a check to ensure that mSeqSlot is set before proceeding with request initialization. |
| cpp/include/tensorrt_llm/batch_manager/createNewDecoderRequests.h | Removed duplicate createDecoderRequests declaration to reduce redundancy. |
Comments suppressed due to low confidence (1)
cpp/tensorrt_llm/batch_manager/createNewDecoderRequests.cpp:663
- Ensure that this check for mSeqSlot includes a descriptive error message or logging to aid in debugging if the invariant is violated.
TLLM_CHECK(llmReq->mSeqSlot.has_value());
|
PR_Github #9004 [ run ] triggered by Bot |
|
PR_Github #9004 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_test
branch
from
8816bf8 to
cfe0d45
Compare
|
/bot run |
|
PR_Github #9060 [ run ] triggered by Bot |
|
PR_Github #9060 [ run ] completed with state |
- Introduced a new helper function, prepareRequest, to encapsulate the logic for creating individual decoder requests. - Updated the prepareRequests function to utilize the new prepareRequest function, improving code readability and maintainability. - This refactor enhances the clarity of request handling within the decoder batch processing. Signed-off-by: Robin Kobus <[email protected]>
- Removed the old prepareRequests function, consolidating request preparation logic into a single location. Signed-off-by: Robin Kobus <[email protected]>
- Moved the request preparation logic to a single function to improve code readability and maintainability. - Moved prepareRequest function into newRequests function. - Updated all calls to newRequests throughout the test file to align with the new signature, improving code clarity and maintainability. Signed-off-by: Robin Kobus <[email protected]>
- Instead of custom method to prepare requests in gptDecoderBatchedTest, create llmRequests. - Use createDecoderRequests method instead of newRequest in gptDecoderBatchedTest. Signed-off-by: Robin Kobus <[email protected]>
- Introduced createLlmRequests function to streamline the creation of LlmRequest objects. - Updated newRequests function to accept a vector of LlmRequest pointers, improving clarity and maintainability. - Refactored test cases to utilize the new createLlmRequests function, ensuring consistent request handling across tests. Signed-off-by: Robin Kobus <[email protected]>
…dTest Signed-off-by: Robin Kobus <[email protected]>
Funatiq
force-pushed
the
dev/refactor_decoder_test
branch
from
cfe0d45 to
157945f
Compare
|
/bot run |
|
PR_Github #9132 [ run ] triggered by Bot |
|
PR_Github #9132 [ run ] completed with state |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
LlmRequests in the test first.createDecoderRequestsfromcreateNewDecoderRequestsinstead of lower levelnewRequestfunction.Please see commit messages for details. This should enable simplifying
createNewDecoderRequests.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 [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]Launch build/test pipelines. All previously running jobs will be killed.
--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 "A10-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-1, 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.--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. Will also run 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-[Post-Merge]-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.md.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.