[None][chore] Enable auto deploy accuracy test in CI #7179
Conversation
Signed-off-by: ajrasane <[email protected]>
📝 WalkthroughWalkthroughAdds a new AutoDeploy dtype accuracy test entry to multiple integration test-list YAMLs and changes the attention custom op to stop sorting indices before applying new tokens; no public APIs or other tests were modified. Changes
Sequence Diagram(s)sequenceDiagram
participant Caller as ModelForward
participant Op as attention_interface.update_input_ids_with_new_tokens
participant Device as GPU_Tensors
Note over Caller,Op: Inputs: input_ids, new_tokens, idx, mask
Caller->>Op: call update_input_ids_with_new_tokens(...)
Op->>Device: ensure tensors on device
alt previous behavior
Op->>Op: sort(idx)
Op->>Op: gather new_tokens[0, sorted_idx, 0]
Op->>Op: masked_scatter using sorted_idx
else new behavior
Op->>Op: gather new_tokens[0, idx, 0]
Op->>Op: masked_scatter using original idx
end
Op->>Caller: return updated input_ids
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
|
/bot run |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/test_lists/test-db/l0_gb200.yml (1)
39-40: Optional: add an explicit timeout budget to protect the pre-merge queue.Many long-running accuracy tests carry a TIMEOUT annotation in these lists. If this auto-deploy flow can occasionally exceed expected runtime, consider adding a conservative timeout to avoid wedging the lane.
Example diff (tweak the budget to your lane’s norms):
- - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype + - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype TIMEOUT (60)
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (6)
tests/integration/test_lists/test-db/l0_b200.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_b200.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h100.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h200.yml(1 hunks)tests/integration/test_lists/test-db/l0_gb200.yml(1 hunks)tests/integration/test_lists/test-db/l0_h100.yml(1 hunks)
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h200.yml
🔇 Additional comments (7)
tests/integration/test_lists/test-db/l0_dgx_b200.yml (1)
92-93: Addition of AutoDeploy test is consistent with the PR objective.The addition of the AutoDeploy test entry with proper header formatting follows the pattern established across other test configuration files in this PR.
tests/integration/test_lists/test-db/l0_b200.yml (1)
72-73: Addition of AutoDeploy test is consistent with the PR objective.The addition of the AutoDeploy test entry with proper header formatting follows the pattern established across other test configuration files in this PR.
tests/integration/test_lists/test-db/l0_dgx_h200.yml (2)
37-38: Addition of AutoDeploy test is consistent with the PR objective.The addition of the AutoDeploy test entry with proper header formatting follows the pattern established across other test configuration files in this PR. This is the first insertion for the 8-GPU configuration.
118-119: AutoDeploy test entries consistent across all test-db filesAll AutoDeploy test sections under
tests/integration/test_lists/test-db/share the same header and test path format:
- Header comment:
# ------------- AutoDeploy tests ---------------- Test entry:
- accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtypeNo discrepancies were detected.
tests/integration/test_lists/test-db/l0_h100.yml (1)
105-106: Addition of AutoDeploy test is consistent with the PR objective.The addition of the AutoDeploy test entry with proper header formatting follows the pattern established across other test configuration files in this PR. The test is appropriately placed in the pre_merge PyTorch backend section.
tests/integration/test_lists/test-db/l0_dgx_h100.yml (1)
64-65: Addition of AutoDeploy test is consistent with the PR objective.The addition of the AutoDeploy test entry with proper header formatting follows the pattern established across other test configuration files in this PR. This is the first insertion for the general pre_merge PyTorch backend section.
tests/integration/test_lists/test-db/l0_gb200.yml (1)
39-40: Verified AutoDeploy dtype test mapping and skip markersAll checks passed for the new AutoDeploy dtype accuracy test in the GB200 pre-merge bucket:
- Consistent inclusion:
The test appears under the “AutoDeploy tests” section in every relevant l0_* YAML (l0_h100, l0_gb200, l0_dgx_h200, l0_dgx_h100, l0_dgx_b200, l0_b200).- Dynamic stage mapping:
Thescripts/test_to_stage_mapping.pyscript dynamically reads each YAML’sterms.stage: pre_mergeentry, so this test will be routed to the correct pre-merge Jenkins stage for GB200.- Skip marker validation:
The only decorator is@pytest.mark.skip_less_device_memory(32000), which does not affect GB200 (each GB200 GPU has ≥32 GB memory), so the test will run as expected.No further changes are needed.
|
PR_Github #16223 [ run ] triggered by Bot |
suyoggupta
changed the title
|
PR_Github #16223 [ run ] completed with state |
Signed-off-by: Suyog Gupta <[email protected]>
|
/bot run |
suyoggupta
requested review from
a team,
galagam and
lucaslie
and removed request for
a team and
lucaslie
|
PR_Github #16252 [ run ] triggered by Bot |
suyoggupta
changed the title
|
PR_Github #16252 [ run ] completed with state |
|
/bot run |
|
PR_Github #16272 [ run ] triggered by Bot |
|
PR_Github #16272 [ run ] completed with state |
|
/bot run |
|
PR_Github #16279 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #16280 [ run ] triggered by Bot |
|
PR_Github #16279 [ reuse-pipeline ] completed with state |
|
PR_Github #16280 [ run ] completed with state |
|
/bot run |
|
PR_Github #16284 [ run ] triggered by Bot |
|
hi @syuoni , Could you take a look and confirm if this is the correct way to add accuracy test to CI? |
|
PR_Github #16284 [ run ] completed with state |
Signed-off-by: Suyog Gupta <[email protected]>
|
/bot reuse-pipeline |
|
PR_Github #16319 [ reuse-pipeline ] triggered by Bot |
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (3)
tests/integration/test_lists/test-db/l0_gb200.yml (2)
1-2: If you must keep tests in this file, mirror the "AutoDeploy tests" header for consistency.Other files introduce an "------------- AutoDeploy tests ---------------" header near the insertion point; this one does not. Consistent headers aid grepping and any lightweight parsers.
Suggested edit near the insertion (if not reverting):
+ # ------------- AutoDeploy tests --------------- - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype
3-18: l0_gb200.yml is unused by any active CI pipeline; it can be safely removedAfter searching the repo for references to
l0_gb200(including Jenkins pipelines, scripts, and docs), the only occurrences are in its own YAML (with a “not used” comment) and a commented-out entry injenkins/L0_Test.groovy. There are no live references to how this test list is consumed. To prevent future drift, please:
- Delete the file
tests/integration/test_lists/test-db/l0_gb200.yml- Remove the stale commented-out entries at around line 1923 in
jenkins/L0_Test.groovytests/integration/test_lists/test-db/l0_dgx_h200.yml (1)
3-16: Consider also adding the AutoDeploy test to the 4-GPU PyTorch post_merge block if intentional parity is desired.The 8-GPU block includes it; the 4-GPU block may or may not need it depending on scheduling goals. If the intent is parity across H200 pools, mirror the addition; if not, leave as-is.
If parity is desired, add under the 4-GPU PyTorch block with a matching header:
tests: + # ------------- AutoDeploy tests --------------- + - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
tests/integration/test_lists/test-db/l0_dgx_h100.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h200.yml(1 hunks)tests/integration/test_lists/test-db/l0_gb200.yml(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/integration/test_lists/test-db/l0_dgx_h100.yml
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h200.ymltests/integration/test_lists/test-db/l0_gb200.yml
⏰ 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)
- GitHub Check: Pre-commit Check
🔇 Additional comments (1)
tests/integration/test_lists/test-db/l0_dgx_h200.yml (1)
37-38: LGTM: cleanly scoped AutoDeploy test addition and header.The grouping header matches conventions used elsewhere; the test path is precise and non-parameterized, which is ideal for stage mapping.
Signed-off-by: Suyog Gupta <[email protected]>
|
/bot reuse-pipeline |
|
PR_Github #16319 [ reuse-pipeline ] completed with state |
|
PR_Github #16321 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #16321 [ reuse-pipeline ] completed with state |
3 participants
Summary by CodeRabbit
Tests
Bug Fixes
Chores
Description
Added auto deploy accuracy test to
test.ymlfilesTest 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 [--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.