[https://nvbugs/5590408][fix] Exclude num of draft tokens from mMaxSeqLenKv #9210
Conversation
📝 WalkthroughWalkthroughIntroduces a new Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes
Pre-merge checks and finishing touches❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Tip 📝 Customizable high-level summaries are now available in beta!You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.
Example instruction:
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 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. Comment |
|
/bot run |
|
PR_Github #24752 [ run ] triggered by Bot. Commit: |
|
PR_Github #24752 [ run ] completed with state |
ziyixiong-nv
force-pushed
the
dev-fxiong-bug5590408
branch
from
58aaac0 to
8fa324d
Compare
|
/bot run |
|
PR_Github #24754 [ run ] triggered by Bot. Commit: |
|
/bot run |
|
PR_Github #24756 [ run ] triggered by Bot. Commit: |
|
PR_Github #24754 [ run ] completed with state |
schetlur-nv
left a comment
schetlur-nv
left a comment
There was a problem hiding this comment.
@ziyixiong-nv looking over this change it seems like a very subtle bug that is not restricted to gpt-oss (or maybe not even 2 model), is that right?
Can we add a unit test to for this issue in the MR, please?
|
Great work @ziyixiong-nv. Seems pretty hard to test this by verifying accuracy end-to-end - shall we add a test that injects a mock model and validates the values of |
|
PR_Github #24756 [ run ] completed with state |
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
ziyixiong-nv
force-pushed
the
dev-fxiong-bug5590408
branch
from
80dfd67 to
c4976a5
Compare
|
/bot run |
Thanks. This is a good idea. I've added a test for it. |
|
PR_Github #24845 [ run ] triggered by Bot. Commit: |
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
ziyixiong-nv
force-pushed
the
dev-fxiong-bug5590408
branch
from
c4976a5 to
9e682cc
Compare
|
/bot run |
|
PR_Github #24846 [ run ] triggered by Bot. Commit: |
|
PR_Github #24845 [ run ] completed with state |
|
PR_Github #24846 [ run ] completed with state |
…qLenKv (NVIDIA#9210) Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com> Signed-off-by: lkomali <lkomali@nvidia.com>
7 participants
Summary by CodeRabbit
Description
The variable
mMaxSeqLenKvin the attention kernel should exclude the draft_tokens, as it's referring to thehost_past_kv_len.By applying this change, the GPQA testing with 1-model spec dec at reasoning high can reach score
0.76, which is similar to the score of no spec dec.There's no single test for this fix. In the GPQA testing, a repetition issue happens more when enabling 1-model spec dec without the fix. However, for a single testing, the test without spec dec could also meet the repetition issue when using some specific tactics.
The PR also removed the unnecessary code in prepare_flash_mla.
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.