fix TMA error with GEMM+AR on TP=2 #6075
Conversation
|
/bot run --add-multi-gpu-test |
|
PR_Github #11980 [ run ] triggered by Bot |
|
PR_Github #11980 [ run ] completed with state |
xavier-nvidia
force-pushed
the
user/xsimmons/gemmARFix
branch
from
ef42193 to
5365b66
Compare
|
/bot run --add-multi-gpu-test |
|
PR_Github #12004 [ run ] triggered by Bot |
|
PR_Github #12004 [ run ] completed with state |
xavier-nvidia
force-pushed
the
user/xsimmons/gemmARFix
branch
from
5365b66 to
af02906
Compare
|
/bot run --add-multi-gpu-test |
|
PR_Github #12015 [ run ] triggered by Bot |
|
PR_Github #12015 [ run ] completed with state |
cpp/tensorrt_llm/plugins/gemmAllReducePlugin/gemmAllReducePluginProfiler.cpp
Show resolved
Hide resolved
xavier-nvidia
force-pushed
the
user/xsimmons/gemmARFix
branch
from
af02906 to
f397d7b
Compare
WalkthroughThe changes remove unused CUDA stream and event management from two kernel workspace classes, update the workspace key handling in the GEMM AllReduce plugin to use a Changes
Sequence Diagram(s)sequenceDiagram
participant Plugin as GemmAllReducePlugin
participant Registry as PluginRegistry
Plugin->>Plugin: allocatePersistentWorkspace()
Plugin->>Plugin: Set mWorkspaceKey based on max M
Plugin->>Registry: acquirePluginResource(mWorkspaceKey.c_str())
Note over Plugin: At enqueue(), check M <= max M
Plugin->>Plugin: terminate()
Plugin->>Registry: releasePluginResource(mWorkspaceKey.c_str())
sequenceDiagram
participant Allocator as NVLSCudaAllocator
participant MPI as MPI Library
Allocator->>MPI: MPI_Group_incl (with COMM_SESSION)
Allocator->>MPI: MPI_Comm_create_group
Allocator->>MPI: Use new_comm for allocation/barrier
Allocator->>MPI: MPI_Comm_free(&new_comm)
Poem
📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (6)
💤 Files with no reviewable changes (2)
🚧 Files skipped from review as they are similar to previous changes (4)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
✨ Finishing Touches
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
Signed-off-by: Xavier Simmons <xsimmons@nvidia.com>
xavier-nvidia
force-pushed
the
user/xsimmons/gemmARFix
branch
from
f397d7b to
18055c0
Compare
|
/bot reuse-pipeline |
|
PR_Github #12252 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #12252 [ reuse-pipeline ] completed with state |
Signed-off-by: Xavier Simmons <xsimmons@nvidia.com>
Signed-off-by: Xavier Simmons <xsimmons@nvidia.com>
Signed-off-by: Xavier Simmons <xsimmons@nvidia.com> Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
4 participants
Description
Fix TMA error with GEMM+AR on TP=2 caused by incorrect workspace allocation.
Additionally, disable gemmAllReducePluginProfiler to reduce complications during testing. This is not needed at the moment because static heuristics select optimal configurations.
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.
Summary by CodeRabbit
New Features
Refactor
Chores