Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 36 additions & 1 deletion jenkins/L0_Test.groovy
Original file line number Diff line number Diff line change
Expand Up @@ -3374,7 +3374,7 @@ def launchTestJobs(pipeline, testFilter)
"GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge",
"auto:gb200-flex",
"l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8",
3,
8,
12,
3
)
Expand All @@ -3387,6 +3387,15 @@ def launchTestJobs(pipeline, testFilter)
16,
4
)
// 5 Nodes
multiNodesSBSAConfigs += buildStageConfigs(
"GB200-20_GPUs-5_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE4-GPU16-Post-Merge",
"auto:gb200-flex",
"l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node4_gpu16",
1,
20,
5
)
// 6 Nodes
multiNodesSBSAConfigs += buildStageConfigs(
"GB200-24_GPUs-6_Nodes-PyTorch-Disagg-PerfSanity-CTX2-NODE1-GPU4-GEN1-NODE4-GPU16-Post-Merge",
Expand All @@ -3396,6 +3405,32 @@ def launchTestJobs(pipeline, testFilter)
24,
6
)
multiNodesSBSAConfigs += buildStageConfigs(
"GB200-24_GPUs-6_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE2-GPU8-GEN1-NODE4-GPU16-Post-Merge",
"auto:gb200-flex",
"l0_gb200_multi_nodes_perf_sanity_ctx1_node2_gpu8_gen1_node4_gpu16",
1,
24,
6
)
// 9 Nodes
multiNodesSBSAConfigs += buildStageConfigs(
"GB200-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE8-GPU32-Post-Merge",
"auto:gb200-flex",
"l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32",
7,
36,
9
)
// 10 Nodes
multiNodesSBSAConfigs += buildStageConfigs(
"GB200-40_GPUs-10_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE2-GPU8-GEN1-NODE8-GPU32-Post-Merge",
"auto:gb200-flex",
"l0_gb200_multi_nodes_perf_sanity_ctx1_node2_gpu8_gen1_node8_gpu32",
1,
40,
10
)
fullSet += multiNodesSBSAConfigs.keySet()

if (env.targetArch == AARCH64_TRIPLE) {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,11 @@ l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8:
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_1k1k_con1024_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120) # failed
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120) # failed
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120) # failed
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX] TIMEOUT (120) # failed
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120) # failed
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_1k1k_con1024_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,6 @@ l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node4_gpu16:
backend: pytorch
tests:
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp1_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb384_mtp0_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb384_mtp0_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp1_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_kimi-k2-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb384_mtp0_ccb-UCX] TIMEOUT (120)
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,8 @@ l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32:
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con256_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb256_mtp3_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_8k1k_con4096_ctx1_dep4_gen1_dep32_eplb256_mtp0_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb384_mtp0_ccb-UCX] TIMEOUT (120)
- perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb384_mtp0_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k2-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_1k1k_con1024_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-UCX] TIMEOUT (120)
# - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-v32-fp4_1k1k_con1024_ctx1_dep4_gen1_dep32_eplb256_mtp3_ccb-UCX] TIMEOUT (120)
Expand Down
5 changes: 5 additions & 0 deletions tests/integration/test_lists/waives.txt
Original file line number Diff line number Diff line change
Expand Up @@ -341,3 +341,8 @@ visual_gen/test_visual_gen_benchmark.py::test_offline_benchmark SKIP (https://nv
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/6050487)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[pp4-mtp_nextn=0-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/6050489)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[pp4-mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/6050489)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-UCX] SKIP (https://nvbugs/5844149)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con2048_ctx1_dep4_gen1_dep32_eplb288_mtp1_ccb-UCX] SKIP (https://nvbugs/5844149)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con256_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-UCX] SKIP (https://nvbugs/5844149)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_128k8k_con128_ctx1_pp8_gen1_dep16_eplb0_mtp2_ccb-UCX] SKIP (https://nvbugs/6060119)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_128k8k_con64_ctx1_pp8_gen1_dep32_eplb0_mtp3_ccb-UCX] SKIP (https://nvbugs/6060119)
Loading