[feat] Enable chunked context for flashinfer

[mikeiovine]

[feat] Enable chunked context for flashinfer

Description

There was a subtle bug preventing us from enabling this. The computation of the last_page_len argument for flashinfer
was wrong in chunked prefill cases.

This will help unblock the chunked attention PR for llama 4.

Test Coverage

Added new llama 3 8B + chunked context accuracy test.

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".

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-pipeline

Reuse 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.

[mikeiovine]

Hey @syuoni, can you verify that I added the tests in the correct way? Thanks

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4417 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4417 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #3179 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4423 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4423 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #3185 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4432 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4432 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #3192 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4574 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4574 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #3290 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4725 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4725 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3409 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4735 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4735 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3417 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #4884 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #4884 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3538 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #5034 [ run ] triggered by Bot

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #5046 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #5034 [ run ] completed with state ABORTED

[tensorrt-cicd]

PR_Github #5046 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3674 completed with status: 'FAILURE'

[mikeiovine]

/bot run

[tensorrt-cicd]

PR_Github #5066 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #5066 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3687 completed with status: 'FAILURE'

[mikeiovine]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #5190 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #5190 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #3787 completed with status: 'FAILURE'

[mikeiovine]

/bot skip --comment "The last DGX test timed out at 90% complete (https://prod.blsm.nvidia.com/sw-tensorrt-top-1/blue/organizations/jenkins/LLM%2Fmain%2FL0_Test-x86_64/detail/L0_Test-x86_64/10947/pipeline/7052). Should be safe to merge given that the vast majority of tests have been run and the remaining tests are unrelated to the code this PR touches."

[tensorrt-cicd]

PR_Github #5250 [ skip ] triggered by Bot

[tensorrt-cicd]

PR_Github #5250 [ skip ] completed with state SUCCESS
Skipping testing for commit f76075a