[None][test] add deepseek and qwen cases for rtx series (#8839)

Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com>

Author: ruodil

tests/integration/defs/perf/pytorch_model_config.py

@@ -119,6 +119,27 @@ def get_model_yaml_config(model_label: str,
                 'enable_chunked_prefill': True,
             }
         },
+        # Deepseek R1 model with CUTLASS backend
+        {
+            'patterns': [
+                'deepseek_r1_nvfp4-bench-pytorch-streaming-float4-maxbs:512-maxnt:5220-input_output_len:4000,2000',
+            ],
+            'config': {
+                'enable_attention_dp': True,
+                'moe_config': {
+                    'backend': 'CUTLASS',
+                    'max_num_tokens': 3072,
+                },
+                'kv_cache_config': {
+                    'dtype': 'fp8',
+                    'free_gpu_memory_fraction': 0.5,
+                },
+                'cuda_graph_config': {
+                    'enable_padding': True,
+                    'batch_sizes': [1, 2, 4, 8, 16, 32, 64],
+                },
+            }
+        },
         # Deepseek_v3_lite_cases
         {
             'patterns':

tests/integration/test_lists/qa/llm_perf_core.yml

@@ -397,10 +397,27 @@ llm_perf_core:
   - perf/test_perf.py::test_perf[llama_v3.3_nemotron_super_49b-bench-pytorch-bfloat16-input_output_len:128,128-tp:2-gpus:2]
   #deepseek_v3_lite
   - perf/test_perf.py::test_perf[deepseek_v3_lite_nvfp4-bench-pytorch-float4-input_output_len:128,128]
+  - perf/test_perf.py::test_perf[deepseek_v3_lite_nvfp4-bench-pytorch-float4-maxbs:1-input_output_len:1000,2000-reqs:10-ep:4-tp:8-gpus:8]
+  - perf/test_perf.py::test_perf[deepseek_v3_lite_nvfp4-bench-pytorch-float4-maxbs:384-maxnt:1536-input_output_len:1000,2000-reqs:10000-con:3072-ep:8-tp:8-gpus:8] TIMEOUT(120) #max throughput test
   - perf/test_perf.py::test_perf[deepseek_v3_lite_nvfp4-bench-pytorch-streaming-float4-input_output_len:128,128]
   - perf/test_perf.py::test_perf[deepseek_v3_lite_fp8-bench-pytorch-float8-input_output_len:128,128]
   #mixtral_8x7b_v0.1
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-pytorch-float16-input_output_len:128,128-tp:2-gpus:2]
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-tp:2-gpus:2]
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-tp:2-gpus:2]
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-kv_cache_dtype:fp8-tp:2-gpus:2]
+
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 8
+    wildcards:
+      gpu:
+      - '*6000*'
+      linux_distribution_name: '*'
+  tests:
+  - perf/test_perf.py::test_perf[qwen3_235b_a22b_fp4-bench-pytorch-float4-input_output_len:1000,2000-con:512-ep:4-gpus:4]
+  - perf/test_perf.py::test_perf[qwen3_235b_a22b_fp4-bench-pytorch-float4-input_output_len:1000,2000-con:512-ep:8-tp:8-gpus:8]
+  - perf/test_perf.py::test_perf[deepseek_r1_nvfp4-bench-pytorch-float4-maxbs:1-input_output_len:1000,2000-reqs:10-ep:4-tp:8-gpus:8] TIMEOUT(120)
+  - perf/test_perf.py::test_perf[deepseek_r1_nvfp4-bench-pytorch-float4-maxbs:384-maxnt:1536-input_output_len:1000,2000-reqs:10000-con:3072-ep:8-tp:8-gpus:8] TIMEOUT(120) #max throughput test
+  - perf/test_perf.py::test_perf[deepseek_r1_nvfp4-bench-pytorch-streaming-float4-maxbs:512-maxnt:5220-input_output_len:4000,2000-reqs:512-ep:8-tp:8-gpus:8]