[None][ci] move qwen3 tests from b200 to gb200 (#7257)

QiJune · web-flow · commit baef70e67e49 · 2025-08-26T11:50:53.000-04:00
Signed-off-by: junq &lt;22017000+QiJune@users.noreply.github.com&gt;
diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
@@ -1820,9 +1820,8 @@ def launchTestJobs(pipeline, testFilter, dockerNode=null)
         "H100_PCIe-CPP-2": ["h100-cr", "l0_h100", 2, 2],
         "H100_PCIe-TensorRT-1": ["h100-cr", "l0_h100", 1, 2],
         "H100_PCIe-TensorRT-2": ["h100-cr", "l0_h100", 2, 2],
-        "B200_PCIe-PyTorch-1": ["b100-ts2", "l0_b200", 1, 3],
-        "B200_PCIe-PyTorch-2": ["b100-ts2", "l0_b200", 2, 3],
-        "B200_PCIe-PyTorch-3": ["b100-ts2", "l0_b200", 3, 3],
+        "B200_PCIe-PyTorch-1": ["b100-ts2", "l0_b200", 1, 2],
+        "B200_PCIe-PyTorch-2": ["b100-ts2", "l0_b200", 2, 2],
         "RTX5090-PyTorch-1": ["rtx-5090", "l0_gb202", 1, 1],
         "RTX5080-TensorRT-1": ["rtx-5080", "l0_gb203", 1, 2],
         "RTX5080-TensorRT-2": ["rtx-5080", "l0_gb203", 2, 2],
@@ -1922,8 +1921,7 @@ def launchTestJobs(pipeline, testFilter, dockerNode=null)
     fullSet += SBSATestConfigs.keySet()
 
     SBSASlurmTestConfigs = [
-        // Not used in the pipeline now
-        // "GB200-PyTorch-1": ["gb200-single", "l0_gb200", 1, 3],
+        "GB200-PyTorch-1": ["gb200-single", "l0_gb200", 1, 1],
         "GB200-4_GPUs-PyTorch-1": ["gb200-x4", "l0_gb200_multi_gpus", 1, 1, 4],
         "GB200-4_GPUs-PyTorch-Post-Merge-1": ["gb200-x4", "l0_gb200_multi_gpus", 1, 1, 4],
     ]
diff --git a/tests/integration/test_lists/test-db/l0_b200.yml b/tests/integration/test_lists/test-db/l0_b200.yml
@@ -31,18 +31,6 @@ l0_b200:
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=none-kv_cache_reuse=False-fp8kv=False-overlap_scheduler=True]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=nvfp4-kv_cache_reuse=True-fp8kv=False-overlap_scheduler=True]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=nvfp4-kv_cache_reuse=True-fp8kv=True-overlap_scheduler=True]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_w4a8_mxfp4[fp8-latency]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_w4a8_mxfp4[mxfp8-latency]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_trtllm-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_trtllm-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[fp8-latency-CUTLASS]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[fp8-latency-TRITON]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[fp8-latency-TRTLLM]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-TRTLLM]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a16_mxfp4[latency-TRTLLM]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton]
diff --git a/tests/integration/test_lists/test-db/l0_gb200.yml b/tests/integration/test_lists/test-db/l0_gb200.yml
@@ -1,5 +1,3 @@
-# Don't add any tests here.
-# Copied from l0_b200.yml but not used in the pipeline now
 version: 0.0.1
 l0_gb200:
 - condition:
@@ -17,23 +15,6 @@ l0_gb200:
       backend: pytorch
   tests:
   # ------------- PyTorch tests ---------------
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4_streaming[stream_interval_4]
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4_streaming[stream_interval_64]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=TRTLLM-mtp_nextn=0-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=2-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=TRTLLM-mtp_nextn=2-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_no_kv_cache_reuse[quant_dtype=none-mtp_nextn=2-fp8kv=False-attention_dp=True-cuda_graph=True-overlap_scheduler=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_no_kv_cache_reuse[quant_dtype=nvfp4-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=none-kv_cache_reuse=True-fp8kv=False-overlap_scheduler=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=none-kv_cache_reuse=False-fp8kv=False-overlap_scheduler=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=nvfp4-kv_cache_reuse=True-fp8kv=False-overlap_scheduler=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_chunked_prefill[quant_dtype=nvfp4-kv_cache_reuse=True-fp8kv=True-overlap_scheduler=True]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_w4a8_mxfp4[fp8-latency]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_w4a8_mxfp4[mxfp8-latency]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=False]
@@ -46,100 +27,3 @@ l0_gb200:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-TRTLLM]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a16_mxfp4[latency-TRTLLM]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton]
-  - disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0] # nvbugs 5300551
-  - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
-  - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]
-  - test_e2e.py::test_ptp_quickstart_advanced_mtp[DeepSeek-V3-Lite-BF16-DeepSeek-V3-Lite/bf16]
-  - test_e2e.py::test_ptp_quickstart_advanced_mixed_precision
-  - test_e2e.py::test_ptp_quickstart_advanced_eagle3[Llama-3.1-8b-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct-EAGLE3-LLaMA3.1-Instruct-8B]
-  - test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct]
-  - test_e2e.py::test_trtllm_bench_pytorch_backend_sanity[meta-llama/Llama-3.1-8B-llama-3.1-8b-False-False]
-  - unittest/_torch/attention
-  - unittest/_torch/compilation
-  - unittest/_torch/debugger
-  - unittest/_torch/executor
-  - unittest/_torch/misc
-  - unittest/_torch/modules
-  - unittest/_torch/multimodal
-  - unittest/_torch/sampler
-  - unittest/_torch/speculative
-  - unittest/_torch/thop
-  - unittest/_torch/modeling -k "modeling_llama"
-  - unittest/_torch/modeling -k "modeling_mixtral"
-  - unittest/_torch/modeling -k "modeling_deepseek"
-  - unittest/_torch/modeling -k "modeling_gpt_oss"
-  - unittest/_torch/auto_deploy/unit/singlegpu -k "not test_trtllm_bench_backend_comparison"
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 1
-        lte: 1
-    wildcards:
-      gpu:
-      - '*gb200*'
-      linux_distribution_name: ubuntu*
-      cpu: aarch64
-    terms:
-      stage: post_merge
-      backend: tensorrt
-  tests:
-  # ------------- TRT tests ---------------
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_nvfp4
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_nvfp4_gemm_plugin[disable_norm_quant_fusion-disable_fused_quant]
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_nvfp4_gemm_plugin[disable_norm_quant_fusion-enable_fused_quant]
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_nvfp4_gemm_plugin[enable_norm_quant_fusion-disable_fused_quant]
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_nvfp4_gemm_plugin[enable_norm_quant_fusion-enable_fused_quant]
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_auto_dtype
-  - accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_fp8
-  - accuracy/test_cli_flow.py::TestMixtral8x7B::test_nvfp4_prequantized
-  - unittest/trt/attention/test_gpt_attention.py -k "trtllm_gen"
-  - unittest/llmapi/test_llm_quant.py
-  - unittest/trt/functional/test_fp4_gemm.py
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 1
-        lte: 1
-    wildcards:
-      gpu:
-      - '*gb200*'
-      linux_distribution_name: ubuntu*
-      cpu: aarch64
-    terms:
-      stage: post_merge
-      backend: triton
-  tests:
-  # ------------- Triton tests ---------------
-  - triton_server/test_triton.py::test_llava[llava]
-  - triton_server/test_triton.py::test_gpt_ib_ptuning[gpt-ib-ptuning]
-  - triton_server/test_triton.py::test_gpt_2b_ib_lora[gpt-2b-ib-lora]
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 1
-        lte: 1
-    wildcards:
-      gpu:
-      - '*gb200*'
-      linux_distribution_name: ubuntu*
-      cpu: aarch64
-    terms:
-      stage: post_merge
-      backend: pytorch
-  tests:
-  # ------------- PyTorch tests ---------------
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=True-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=2-fp8kv=True-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=True-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=True-cuda_graph=False-overlap_scheduler=False-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=True-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=TRTLLM-mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=2-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=TRTLLM-mtp_nextn=2-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False]
