[TRTLLM-9687][feat] Improve are_stop_words performance#11196
[TRTLLM-9687][feat] Improve are_stop_words performance#11196stnie merged 10 commits intoNVIDIA:mainNVIDIA/TensorRT-LLM:mainfrom stnie:develop/sampler/are_stop_words_perfstnie/TensorRT-LLM:develop/sampler/are_stop_words_perfCopy head branch name to clipboard
Conversation
6dd8988 to
a9d586d
Compare
|
/bot run --disable-fail-fast |
1 similar comment
|
/bot run --disable-fail-fast |
|
PR_Github #34510 [ run ] triggered by Bot. Commit: |
|
PR_Github #34510 [ run ] completed with state
|
Funatiq
left a comment
There was a problem hiding this comment.
Do we have unit tests to verify the stop words functionality?
128186f to
87098cd
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #36093 [ run ] triggered by Bot. Commit: |
|
PR_Github #36093 [ run ] completed with state
|
4b9cd74 to
db39bf7
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #36163 [ run ] triggered by Bot. Commit: |
|
PR_Github #36163 [ run ] completed with state
|
|
/bot run |
|
PR_Github #36223 [ run ] triggered by Bot. Commit: |
|
PR_Github #36223 [ run ] completed with state
|
09b8088 to
867daab
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #36229 [ run ] triggered by Bot. Commit: |
|
PR_Github #36229 [ run ] completed with state
|
769c8c9 to
bf6847d
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #36260 [ run ] triggered by Bot. Commit: |
…nd updated testcase - Updated wrong/stale docstrings and reformatted them to be more uniform - Fixed a previously introduced bug, where drafts did not update their finish reasons - Updated test_torch_sampler to test write_finish_reasons, which combines _prepare_stop_word_handling_for_finish_reasons and _write_finish_reasons Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
75236af to
6fe07d7
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #36956 [ run ] triggered by Bot. Commit: |
|
PR_Github #36956 [ run ] completed with state
|
|
/bot run |
|
PR_Github #37051 [ run ] triggered by Bot. Commit: |
|
PR_Github #37051 [ run ] completed with state |
d9ce57e to
da7fd2e
Compare
|
/bot run --disable-fail-fast |
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
da7fd2e to
c1297fe
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #37098 [ run ] triggered by Bot. Commit: |
|
PR_Github #37098 [ run ] completed with state
|
|
/bot run |
|
PR_Github #37309 [ run ] triggered by Bot. Commit: |
|
PR_Github #37309 [ run ] completed with state
|
|
/bot run |
|
PR_Github #37323 [ run ] triggered by Bot. Commit: |
|
PR_Github #37323 [ run ] completed with state |
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
Summary by CodeRabbit
Description
Improve are_stop_words performance by caching stop words and past tokens in the TorchSampler Store.
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
Update tava architecture diagram if there is a significant design change in PR.
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.
Details
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.