[fix] Update to properly set cuda graphs in trtllm-bench overrides. #5634
Conversation
|
/bot run |
|
PR_Github #10440 [ run ] triggered by Bot |
|
PR_Github #10440 [ run ] completed with state |
FrankD412
force-pushed
the
fdinatale/trtllm-bench/fix_cg_overrides
branch
from
96a1922 to
126cb56
Compare
|
I was working with @Jie-Fang and Amey -- it turned out we couldn't actually disable the CUDA graphs because the configuration checks for existence. |
|
/bot run |
Signed-off-by: Frank Di Natale <[email protected]>
Signed-off-by: Frank Di Natale <[email protected]>
Signed-off-by: Frank Di Natale <[email protected]>
FrankD412
force-pushed
the
fdinatale/trtllm-bench/fix_cg_overrides
branch
from
3e22639 to
c61417d
Compare
|
PR_Github #10543 [ run ] triggered by Bot |
|
PR_Github #10543 [ run ] completed with state |
|
/bot run |
|
PR_Github #10578 [ run ] triggered by Bot |
|
PR_Github #10578 [ run ] completed with state |
|
/bot run |
|
PR_Github #10682 [ run ] triggered by Bot |
|
PR_Github #10682 [ run ] completed with state |
|
/bot run |
|
/bot run |
|
PR_Github #10893 [ run ] triggered by Bot |
|
PR_Github #10893 [ run ] completed with state |
|
/bot run |
|
/bot kill |
Signed-off-by: Frank Di Natale <[email protected]>
|
PR_Github #10965 [ run ] triggered by Bot |
Signed-off-by: Frank Di Natale <[email protected]>
|
PR_Github #10966 [ kill ] triggered by Bot |
|
PR_Github #10965 [ run ] completed with state |
|
PR_Github #10966 [ kill ] completed with state |
|
/bot run |
|
PR_Github #10967 [ run ] triggered by Bot |
|
PR_Github #10967 [ run ] completed with state |
|
/bot run |
|
PR_Github #11023 [ run ] triggered by Bot |
|
PR_Github #11023 [ run ] completed with state |
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]>
…VIDIA#5634) Signed-off-by: Frank Di Natale <[email protected]> Signed-off-by: Yuxin <[email protected]>
Description
This PR fixes the LLM API overrides for the YAML config to
trtllm-benchandtrtllm-serverelated to the recent CUDA graph. The recent updates didn't update the utility function and the checks within the settings generation for bench so this PR fixes those issues.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.