[None][test] CI bisect nvbugs/6280721: probe b4d44d3 (unwaive GPT-OSS w4 DP4 CUTLASS #14884)

[tensorrt-cicd]

Purpose

Pre-merge CI bisect probe for nvbugs/6280721. This PR isolates the wider-window probe at commit a8c4007 ([None][fix] Fix AutoDeploy accuracy tests #13925) — the commit immediately before the parent baseline 910826b — by basing the PR on its parent 33b0a32.

Background

a8c4007 is one step further back from the existing baseline probe (#15242). Combined with the other two probes (#15241 culprit 8e5d9e2, #15242 parent 910826b), this widens the bisect window to confirm the regression at 8e5d9e2 is not pre-existing earlier in the chain.

Expected Result

This test should pass here.

Test Under Observation

perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_1k1k_con2048_ctx1_dep4_gen1_dep4_eplb0_mtp1_ccb-NIXL]

Waiver Note

The test case is not present in tests/integration/test_lists/waives.txt at this commit, so no waiver removal is needed.

[chenfeiz0326]

/bot run --disable-fail-fast --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE1-GPU4-Post-Merge-4"

[tensorrt-cicd]

PR_Github #53564 [ run ] triggered by Bot. Commit: 3d7d88d Link to invocation

[tensorrt-cicd]

PR_Github #53564 [ run ] completed with state FAILURE. Commit: 3d7d88d
/LLM/main/L0_MergeRequest_PR pipeline #42713 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[chenfeiz0326]

/bot run --disable-fail-fast --stage-list "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-7,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-5"

[tensorrt-cicd]

PR_Github #54244 [ run ] triggered by Bot. Commit: b4d44d3 Link to invocation

[tensorrt-cicd]

PR_Github #54244 [ run ] completed with state SUCCESS. Commit: b4d44d3
/LLM/main/L0_MergeRequest_PR pipeline #43318 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[chenfeiz0326]

/bot run --disable-fail-fast --stage-list "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-7,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-5"

[tensorrt-cicd]

PR_Github #54305 [ run ] triggered by Bot. Commit: 91684c4 Link to invocation

[tensorrt-cicd]

PR_Github #54305 [ run ] completed with state SUCCESS. Commit: 91684c4
/LLM/main/L0_MergeRequest_PR pipeline #43376 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation