[nvbugs/5336321][fix] Enable attention dp = False test case, Fix TRTLLM Gen Moe workspace allocation

[yizhang-nv]

PR title

This pr fix the illegal memory access encountered at cudaMemsetAsync at this line:

TensorRT-LLM/cpp/tensorrt_llm/kernels/trtllmGenKernels/blockScaleMoe/RoutingKernel.cu

Line 1254 in 312fd47

TLLM_CUDA_CHECK(cudaMemsetAsync(

It memset the buffer at max size (max num threads * 2), however, we don't allocate that large space. This pr increase the buffer size to the max size as well.

Description

Please explain the issue and the solution in short.

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

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.

[yizhang-nv]

/bot run

[tensorrt-cicd]

PR_Github #9823 [ run ] triggered by Bot

[yizhang-nv]

/bot run

[tensorrt-cicd]

PR_Github #9837 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9823 [ run ] completed with state ABORTED

[tensorrt-cicd]

PR_Github #9837 [ run ] completed with state FAILURE
/LLM/release-0.21/L0_MergeRequest_PR pipeline #28 completed with status: 'FAILURE'

[yizhang-nv]

/bot run

[tensorrt-cicd]

PR_Github #9840 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9840 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #29 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

[yizhang-nv]

/bot run --stage-list "GB200-4_GPUs-PyTorch-[Post-Merge]-1"

[tensorrt-cicd]

PR_Github #9906 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9906 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #32 (Partly Tested) completed with status: 'SUCCESS'

[yizhang-nv]

/bot run --stage-list "GB200-4_GPUs-PyTorch-[Post-Merge]-1"

[tensorrt-cicd]

PR_Github #10582 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10582 [ run ] completed with state FAILURE
/LLM/release-0.21/L0_MergeRequest_PR pipeline #104 (Partly Tested) completed with status: 'FAILURE'

[yizhang-nv]

/bot run --stage-list "GB200-4_GPUs-PyTorch-[Post-Merge]-1"

[yizhang-nv]

/bot run

[tensorrt-cicd]

PR_Github #10757 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10757 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #140 completed with status: 'FAILURE'

[yizhang-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #10774 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10774 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #146 completed with status: 'FAILURE'

[yizhang-nv]

/bot run --disable-fail-fast --add-multi-gpu-test

[tensorrt-cicd]

PR_Github #10927 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10927 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #160 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

[yizhang-nv]

/bot run --stage-list "GB200-4_GPUs-PyTorch-[Post-Merge]-1"

[tensorrt-cicd]

PR_Github #11003 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #11003 [ run ] completed with state SUCCESS
/LLM/release-0.21/L0_MergeRequest_PR pipeline #167 (Partly Tested) completed with status: 'SUCCESS'

[yizhang-nv]

/bot skip --comment "All related tests are passed"

[tensorrt-cicd]

PR_Github #11015 [ skip ] triggered by Bot

[tensorrt-cicd]

PR_Github #11015 [ skip ] completed with state SUCCESS
Skipping testing for commit eff3a08