diff --git a/tests/integration/defs/perf/pytorch_model_config.py b/tests/integration/defs/perf/pytorch_model_config.py
index 88766ad767d..5851ea3fcef 100644
--- a/tests/integration/defs/perf/pytorch_model_config.py
+++ b/tests/integration/defs/perf/pytorch_model_config.py
@@ -18,7 +18,7 @@
 """
 
 
-def get_model_yaml_config(model_label: str, input_lens: list[int]) -> dict:
+def get_model_yaml_config(model_label: str) -> dict:
     """
         Return the yaml config corresponding to the model label.
         Args:
diff --git a/tests/integration/test_lists/qa/trt_llm_release_perf_cluster_test.yml b/tests/integration/test_lists/qa/trt_llm_release_perf_cluster_test.yml
index 4d7172b89fc..7092bdad494 100644
--- a/tests/integration/test_lists/qa/trt_llm_release_perf_cluster_test.yml
+++ b/tests/integration/test_lists/qa/trt_llm_release_perf_cluster_test.yml
@@ -21,7 +21,6 @@ trt_llm_release_perf_cluster_test:
   - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-float8-maxbs:256-input_output_len:128,128-gpus:2]
   - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-float8-maxbs:256-input_output_len:512,32-gpus:2]
   - perf/test_perf.py::test_perf[llama_v2_13b-bench-float16-input_output_len:128,128-loras:8-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:2]
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-quant:fp8-gpus:2]
 
 # Tests for systems with 4+ GPUs
@@ -34,7 +33,7 @@ trt_llm_release_perf_cluster_test:
   - perf/test_perf.py::test_perf[qwen_14b_chat-bench-float16-input_output_len:128,128-gpus:4]
   - perf/test_perf.py::test_perf[qwen_14b_chat-bench-float16-input_output_len:512,32-gpus:4]
   - perf/test_perf.py::test_perf[starcoder_15b-bench-float16-input_output_len:512,200-gpus:4]
-  - perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:4]
+  #- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:4]
 
 # Tests for systems with 8+ GPUs
 - condition:
@@ -42,8 +41,9 @@ trt_llm_release_perf_cluster_test:
       system_gpu_count:
         gte: 8
   tests:
-  - perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:512,32-gpus:8]
+  #- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128-gpus:8]
+  #- perf/test_perf.py::test_perf[llama_v3.1_405b_instruct_fp4-bench-pytorch-float4-input_output_len:512,32-gpus:8]
+  - perf/test_perf.py::test_perf[llama_v3.3_nemotron_super_49b-bench-bfloat16-input_output_len:500,2000-quant:fp8-con:250-gpus:8]
   - perf/test_perf.py::test_perf[mixtral_8x22b_v0.1-bench-float16-input_output_len:512,512-quant:fp8-tp:8]
   - perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:128,128-reqs:80-gpus:8]
   - perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:512,32-reqs:80-gpus:8]
diff --git a/tests/integration/test_lists/qa/trt_llm_release_perf_test.yml b/tests/integration/test_lists/qa/trt_llm_release_perf_test.yml
index 12ed5a8b000..ecd5aa0295d 100644
--- a/tests/integration/test_lists/qa/trt_llm_release_perf_test.yml
+++ b/tests/integration/test_lists/qa/trt_llm_release_perf_test.yml
@@ -1,5 +1,6 @@
 version: 0.0.1
 trt_llm_release_perf_test:
+# one gpu test
 - condition:
     ranges:
       system_gpu_count:
@@ -18,52 +19,18 @@ trt_llm_release_perf_test:
   - perf/test_perf.py::test_perf[roberta_base-cpp-plugin-float16-bs:32+64-input_len:128+512]
 
   # E2E gptManagerBenchmark IFB
-  - perf/test_perf.py::test_perf[gpt_350m_moe-cppmanager-exe-plugin-float16-bs:64-input_output_len:128,8+512,32]
-  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-static_batching-plugin_ifb-float16-bs:8+64-input_output_len:128,128+512,32] #oom for l40s
-  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-plugin_ifb-float16-mp-input_output_len:128,128+512,32] #oom for l40s
-  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-plugin_ifb-bfloat16-gwp:0.0-input_output_len:128,128+512,32] #oom for l40s
-  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-plugin_ifb-bfloat16-gwp:0.5-input_output_len:128,128+512,32] #oom for l40s
-
   # E2E ENC-DEC
   - perf/test_perf.py::test_perf[t5_large-cppmanager-exe-plugin_ifb-float16-mp-input_output_len:128,20]
 
   # E2E trtllm-bench
   - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-streaming-bfloat16-input_output_len:128,128]
   - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-streaming-bfloat16-input_output_len:512,32]
-  # Llama-3.1-Nemotron-Nano-8B-v1
-  # cpp backend
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-quant:fp8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-quant:fp8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-quant:fp8-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-quant:fp8-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:250]
-  # pyt backend
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-maxnt:5000-input_output_len:5000,500-reqs:8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:500,2000-reqs:8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:1000,1000-reqs:8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-maxnt:20000-input_output_len:20000,2000-reqs:8-con:1]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:5000,500-reqs:500-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:500,2000-reqs:500-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:1000,1000-reqs:500-con:250]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:20000,2000-reqs:500-con:250]
 
   - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:128,128]
   - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:512,32]
   - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128]
   - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-pytorch-bfloat16-input_output_len:128,128]
   - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:512,32]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-con:8]
   - perf/test_perf.py::test_perf[qwen2_7b_instruct-bench-float16-input_output_len:128,128]
   - perf/test_perf.py::test_perf[starcoder2_3b-bench-pytorch-float16-input_output_len:512,200]
   - perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-input_output_len:128,128]
@@ -82,10 +49,7 @@ trt_llm_release_perf_test:
 
   # Phi-4-mini-instruct
   # cpp
-  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-con:1]
-  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-quant:fp8-con:1]
   - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-con:250]
-  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-quant:fp8-con:250]
   - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-con:250]
   - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-quant:fp8-con:250]
   # reduced 'reqs' to fit timeout limit
@@ -97,72 +61,118 @@ trt_llm_release_perf_test:
 - condition:
     ranges:
       system_gpu_count:
-        gte: 2
+        gte: 1
+    wildcards:
+      gpu:
+      - '*h100*'
+      - '*h200*'
+      - '*h20*'
+  tests:
+  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-static_batching-plugin_ifb-float16-bs:8+64-input_output_len:128,128+512,32] #oom for l40s, l20(cuda_runtime_error)
+  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-plugin_ifb-float16-mp-input_output_len:128,128+512,32] #oom for l40s, l20（cuda_runtime_error）#44, mpi abort on a100 36
+  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-plugin_ifb-bfloat16-gwp:0.0-input_output_len:128,128+512,32] #oom for l40s, l20, mpi abort on a100 35
+  - perf/test_perf.py::test_perf[llama_v3_8b_instruct-cppmanager-exe-plugin_ifb-bfloat16-gwp:0.5-input_output_len:128,128+512,32] #oom for l40s, l20
+  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-con:1] # timeout for l20, l40s
+
+  # Llama-3.1-Nemotron-Nano-8B-v1
+  # cpp backend
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-con:250]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:250]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:250]
+  # pyt backend
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-maxnt:5000-input_output_len:5000,500-reqs:8-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:500,2000-reqs:8-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:1000,1000-reqs:8-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-maxnt:20000-input_output_len:20000,2000-reqs:8-con:1]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:500,2000-reqs:500-con:250]
+  #long time llama_nemotron cases
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-con:1] # timeout for l20, l40s, a100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-quant:fp8-con:1] #timeout for l20, l40s, failed for a100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-quant:fp8-con:1] # timeout for l20, l40s, failed on a100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:5000,500-quant:fp8-con:250] # failed for a100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:250] # failed on A100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-quant:fp8-con:250] # failed on A100 15
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:250] # timeout for l20, l40s, a100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:250] # timeout for l20, l40s, failed on A100
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:5000,500-reqs:500-con:250] # failed for l20, need to extend context token to 5000 for l40s and a100， timeout for h20
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:1000,1000-reqs:500-con:250]
+  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:20000,2000-reqs:500-con:250] #need to extend context token to 20000 for l40s, timeout for h20, a100
+  # deepseek_v3_lite_fp8
+  - perf/test_perf.py::test_perf[deepseek_v3_lite_fp8-bench-pytorch-float8-input_output_len:128,128] # not supported on L20, L40S
+
+# FP8 specific tests
+- condition:
+    terms:
+      supports_fp8: true
     wildcards:
       gpu:
       - '*h100*'
       - '*h200*'
-      - '*a100*'
       - '*l40s*'
       - '*l20*'
       - '*h20*'
   tests:
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-cppmanager-exe-plugin_ifb-bfloat16-mp-maxbs:256-input_output_len:128,128-pp:2]
-  - perf/test_perf.py::test_perf[t5-bench-float16-input_output_len:128,20-gpus:2]
-  - perf/test_perf.py::test_perf[flan_t5_large-bench-float16-input_output_len:128,20-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-streaming-bfloat16-input_output_len:128,128-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:128,128-gpus:2]
-  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-loras:8-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:5000,500-con:1-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:5000,500-con:250-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:128,128-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-cppmanager-exe-plugin_ifb-float16-maxbs:256-input_output_len:128,128-beams:4-quant:fp8]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:fp8]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:w4a16_awq]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:w4a8_awq]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:128,128-quant:fp8]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:512,32-quant:fp8]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:128,128-quant:fp8]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128]
+  - perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-maxbs:256-input_output_len:1000,1000-quant:fp8]
+  - perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-maxbs:256-input_output_len:500,2000-quant:fp8]
+  - perf/test_perf.py::test_perf[phi_3_mini_4k_instruct-bench-float16-maxbs:128-input_output_len:1000,1000-quant:fp8]
+  - perf/test_perf.py::test_perf[phi_3_mini_4k_instruct-bench-float16-maxbs:64-input_output_len:500,2000-quant:fp8]
 
 - condition:
-    ranges:
-      system_gpu_count:
-        gte: 2
-      gpu_memory:
-        gt: 80000
+    terms:
+      supports_fp8: true
     wildcards:
       gpu:
       - '*h100*'
       - '*h200*'
-      - '*a100*'
       - '*h20*'
   tests:
-  - perf/test_perf.py::test_perf[llama_70b_sq_per_tensor-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128+512,32-gpus:2]
-  - perf/test_perf.py::test_perf[mixtral_8x7b-cppmanager-exe-plugin_ifb-float16-mp-input_output_len:128,128+512,32-gpus:2]
-  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128+512,32-gpus:2]
-  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-streaming-float16-input_output_len:128,128-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-maxbs:256-input_output_len:1000,1000-quant:fp8] # mabs 256 for L20, L40S
+  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-quant:fp8-con:1]
+  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-quant:fp8-con:250]
+  - perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-quant:fp8-con:250]
 
+# 2 gpus test
 - condition:
     ranges:
       system_gpu_count:
-        gte: 4
+        gte: 2
     wildcards:
       gpu:
       - '*h100*'
       - '*h200*'
       - '*a100*'
       - '*l40s*'
+      - '*l20*'
       - '*h20*'
-
   tests:
-  - perf/test_perf.py::test_perf[flan_t5_xxl-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128-gpus:4]
-  - perf/test_perf.py::test_perf[flan_t5_xxl-cppmanager-exe-plugin_ifb-float16-input_output_len:512,32-gpus:4]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-streaming-bfloat16-input_output_len:128,128-gpus:4]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:128,128-gpus:4]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:512,32-gpus:4]
-  - perf/test_perf.py::test_perf[qwen_14b_chat-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128-gpus:4]
-  - perf/test_perf.py::test_perf[qwen_14b_chat-cppmanager-ootb_except_mha-float16-input_output_len:128,128+512,32-gpus:4]
-  - perf/test_perf.py::test_perf[starcoder_15.5b-cppmanager-exe-plugin_ifb-float16-maxbs:1-input_output_len:512,200-reqs:10-gpus:4]
-  - perf/test_perf.py::test_perf[starcoder_15.5b-cppmanager-ootb_except_mha-float16-maxbs:1-input_output_len:512,200-reqs:10-gpus:4]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-cppmanager-exe-plugin_ifb-bfloat16-mp-maxbs:256-input_output_len:128,128-pp:2]
+  - perf/test_perf.py::test_perf[t5-bench-float16-input_output_len:128,20-gpus:2]
+  - perf/test_perf.py::test_perf[flan_t5_large-bench-float16-input_output_len:128,20-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-streaming-bfloat16-input_output_len:128,128-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:128,128-gpus:2]
+  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-loras:8-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:5000,500-con:1-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:5000,500-con:250-gpus:2]
+  - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:128,128-gpus:2]
 
 - condition:
     ranges:
       system_gpu_count:
-        gte: 8
+        gte: 2
       gpu_memory:
         gt: 80000
     wildcards:
@@ -172,71 +182,15 @@ trt_llm_release_perf_test:
       - '*a100*'
       - '*h20*'
   tests:
-  # E2E trtllm-bench
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-tp:2-gpus:2]
   - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-loras:8-tp:2-gpus:2]
-  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct-bench-float16-input_output_len:128,128-reqs:64-gpus:8]
-  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct-bench-float16-input_output_len:128,128-reqs:64-con:50-gpus:8]
-  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct-bench-float16-input_output_len:128,128-reqs:64-con:1-gpus:8]
   - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:1024,1024-tp:2-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-cppmanager-exe-plugin_ifb-float16-input_output_len:200,2000-reqs:64-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:200,2000-reqs:64-con:200-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:200,2000-reqs:64-con:1-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:2000,200-reqs:64-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-gpus:8]
-  - perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:128,128-reqs:80-gpus:8]
-  - perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:512,32-reqs:80-gpus:8]
-  # Llama-3_1-Nemotron-Ultra-253B-v1
-  # all cpp backend, bf16->fp8 post-quantized
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_ultra_253b-bench-bfloat16-maxbs:64-input_output_len:5000,500-quant:fp8-reqs:8-con:1-tp:8-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_ultra_253b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-reqs:8-con:1-tp:8-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_ultra_253b-bench-bfloat16-maxbs:64-input_output_len:5000,500-quant:fp8-reqs:250-con:250-tp:8-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.1_nemotron_ultra_253b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-reqs:250-con:250-tp:8-gpus:8]
-
-
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 8
-      gpu_memory:
-        gt: 100000
-    wildcards:
-      gpu:
-      - '*h200*'
-      - '*h20*'
-  tests:
-  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8]
-  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-streaming-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8]
-  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:1-input_output_len:1000,2000-reqs:10-con:1-ep:4-tp:8-gpus:8] #min latency test
-  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:128-maxnt:1127-input_output_len:1000,2000-reqs:5120-con:1024-ep:8-tp:8-gpus:8] #max throughput test
+  - perf/test_perf.py::test_perf[llama_70b_sq_per_tensor-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128+512,32-gpus:2]
+  - perf/test_perf.py::test_perf[mixtral_8x7b-cppmanager-exe-plugin_ifb-float16-mp-input_output_len:128,128+512,32-gpus:2]
+  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-gpus:2]
+  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-streaming-float16-input_output_len:128,128-gpus:2]
 
 # FP8 specific tests
-- condition:
-    terms:
-      supports_fp8: true
-    wildcards:
-      gpu:
-      - '*h100*'
-      - '*h200*'
-      - '*l40s*'
-      - '*l20*'
-      - '*h20*'
-  tests:
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-cppmanager-exe-plugin_ifb-float16-maxbs:256-input_output_len:128,128-beams:4-quant:fp8]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:fp8]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:w4a16_awq]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:w4a8_awq]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:128,128-quant:fp8]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:512,32-quant:fp8]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:1000,1000-quant:fp8]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:128,128-quant:fp8]
-  - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128]
-  - perf/test_perf.py::test_perf[deepseek_v3_lite_fp8-bench-pytorch-float8-input_output_len:128,128]
-  - perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-maxbs:256-input_output_len:1000,1000-quant:fp8]
-  - perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-maxbs:256-input_output_len:500,2000-quant:fp8]
-  - perf/test_perf.py::test_perf[phi_3_mini_4k_instruct-bench-float16-maxbs:128-input_output_len:1000,1000-quant:fp8]
-  - perf/test_perf.py::test_perf[phi_3_mini_4k_instruct-bench-float16-maxbs:64-input_output_len:500,2000-quant:fp8]
-
 - condition:
     terms:
       supports_fp8: true
@@ -281,6 +235,31 @@ trt_llm_release_perf_test:
   - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:500,2000-quant:fp8-con:1-gpus:2]
   - perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:500,2000-quant:fp8-con:250-gpus:2]
 
+# 4 gpus test
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 4
+    wildcards:
+      gpu:
+      - '*h100*'
+      - '*h200*'
+      - '*a100*'
+      - '*l40s*'
+      - '*h20*'
+
+  tests:
+  - perf/test_perf.py::test_perf[flan_t5_xxl-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128-gpus:4]
+  - perf/test_perf.py::test_perf[flan_t5_xxl-cppmanager-exe-plugin_ifb-float16-input_output_len:512,32-gpus:4]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-streaming-bfloat16-input_output_len:128,128-gpus:4]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:128,128-gpus:4]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:512,32-gpus:4]
+  - perf/test_perf.py::test_perf[qwen_14b_chat-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128-gpus:4]
+  - perf/test_perf.py::test_perf[qwen_14b_chat-cppmanager-ootb_except_mha-float16-input_output_len:128,128+512,32-gpus:4]
+  - perf/test_perf.py::test_perf[starcoder_15.5b-cppmanager-exe-plugin_ifb-float16-maxbs:1-input_output_len:512,200-reqs:10-gpus:4]
+  - perf/test_perf.py::test_perf[starcoder_15.5b-cppmanager-ootb_except_mha-float16-maxbs:1-input_output_len:512,200-reqs:10-gpus:4]
+
+# FP8 specific tests
 - condition:
     terms:
       supports_fp8: true
@@ -308,6 +287,63 @@ trt_llm_release_perf_test:
   - perf/test_perf.py::test_perf[llama_v3.3_nemotron_super_49b-bench-bfloat16-maxbs:16-input_output_len:500,2000-con:250-gpus:4]
   - perf/test_perf.py::test_perf[llama_v3.3_nemotron_super_49b-bench-bfloat16-maxbs:16-input_output_len:500,2000-quant:fp8-con:250-gpus:4]
 
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 8
+      gpu_memory:
+        gt: 80000
+    wildcards:
+      gpu:
+      - '*h100*'
+      - '*h200*'
+      - '*a100*'
+      - '*h20*'
+  tests:
+  # E2E trtllm-bench
+  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-cppmanager-exe-plugin_ifb-float16-input_output_len:200,2000-reqs:64-gpus:8]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:200,2000-reqs:64-con:200-gpus:8]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-pytorch-bfloat16-input_output_len:200,2000-reqs:64-con:200-gpus:8]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:200,2000-reqs:64-con:1-gpus:8] # timeout for h20, move to l2 test
+  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:2000,200-reqs:64-gpus:8]
+  - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-gpus:8]
+  - perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:128,128-reqs:80-gpus:8]
+  - perf/test_perf.py::test_perf[gpt_20b-bench-float16-maxbs:8-input_output_len:512,32-reqs:80-gpus:8]
+
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 8
+      gpu_memory:
+        gt: 80000
+    wildcards:
+      gpu:
+      - '*h100*'
+      - '*h200*'
+      - '*h20*'
+  tests:
+  # E2E trtllm-bench
+  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct-bench-float16-input_output_len:128,128-reqs:64-gpus:8] # timeout for a100
+  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct-bench-float16-input_output_len:128,128-reqs:64-con:50-gpus:8] # timeout for a100
+  - perf/test_perf.py::test_perf[mixtral_8x7b_v0.1_instruct-bench-float16-input_output_len:128,128-reqs:64-con:1-gpus:8] # timeout for a100
+
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 8
+      gpu_memory:
+        gt: 100000
+    wildcards:
+      gpu:
+      - '*h200*'
+      - '*h20*'
+  tests:
+  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8]
+  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-streaming-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8]
+  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:1-input_output_len:1000,2000-reqs:10-con:1-ep:4-tp:8-gpus:8] #min latency test
+  - perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:128-maxnt:1127-input_output_len:1000,2000-reqs:5120-con:1024-ep:8-tp:8-gpus:8] #max throughput test
+
+# FP8 specific tests
 - condition:
     terms:
       supports_fp8: true
@@ -327,7 +363,7 @@ trt_llm_release_perf_test:
   - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-gpus:8]
   - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:512,32-gpus:8]
   - perf/test_perf.py::test_perf[llama_v3.3_nemotron_49b-bench-pytorch-float8-input_output_len:128,128-gpus:8]
-  - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-streaming-float8-input_output_len:128,128-gpus:8]
+  - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-streaming-float8-input_output_len:128,128-gpus:8] # timeout for l40s
 
 # GB chip specific tests
 - condition:
@@ -343,7 +379,7 @@ trt_llm_release_perf_test:
   - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128]
   - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp4-bench-pytorch-float4-input_output_len:128,128]
   - perf/test_perf.py::test_perf[llama_v3.1_70b-bench-pytorch-bfloat16-input_output_len:128,128-tp:2-gpus:2]
-  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128]
+  - perf/test_perf.py::test_perf[llama_v3.1_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128] # timeout for h20
   - perf/test_perf.py::test_perf[llama_v3.3_nemotron_49b-bench-pytorch-bfloat16-input_output_len:128,128-tp:2-gpus:2]
   - 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_fp8-bench-pytorch-float8-input_output_len:128,128]
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index be6f31e2e48..dddf29f6451 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -480,53 +480,16 @@ disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8[Dee
 disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_attention_dp[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5232406)
 disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_attention_dp_one[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5232406)
 disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_attention_dp_one_mtp[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5232406)
-full:B200/examples/test_gemma.py::test_llm_gemma_1gpu_summary_vswa[gemma-3-1b-it-other-bfloat16-8] SKIP (https://nvbugs/5292737)
-perf/test_perf.py::test_perf[mixtral_8x22b_v0.1-bench-float16-input_output_len:512,512-quant:fp8-tp:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:128,128-gpus:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_70b-bench-streaming-bfloat16-input_output_len:128,128-gpus:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-quant:fp8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:512,32-quant:fp8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-float8-input_output_len:512,32-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-float8-input_output_len:128,128-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-streaming-bfloat16-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-input_output_len:500,2000-quant:fp8-tp:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[phi_3_mini_128k_instruct-bench-float16-maxbs:128-input_output_len:1000,1000-quant:fp8-tp:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-streaming-bfloat16-input_output_len:128,128-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:128,128-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[phi_3_mini_128k_instruct-bench-float16-maxbs:128-input_output_len:500,2000-quant:fp8-tp:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mistral_7b_v0.1-bench-float16-input_output_len:1000,1000-quant:fp8-tp:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:w4a8_awq] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[qwen2_7b_instruct-bench-float16-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:128-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:128,128-quant:fp8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-maxbs:256-input_output_len:128,128-quant:fp8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:fp8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:w4a16_awq] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:512,32-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mixtral_8x22b_v0.1-bench-bfloat16-input_output_len:512,512-quant:fp8-tp:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-tp:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-input_output_len:128,128-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.3_nemotron_49b-bench-pytorch-float8-input_output_len:128,128-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:1-input_output_len:1000,2000-reqs:10-con:1-ep:4-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:128-maxnt:1127-input_output_len:1000,2000-reqs:5120-con:1024-ep:8-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[deepseek_r1_fp8-bench-pytorch-streaming-float8-maxbs:32-input_output_len:128,128-ep:8-tp:8-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:512,200-quant:fp8-tp:4] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-cppmanager-exe-plugin_ifb-float16-input_output_len:200,2000-reqs:64-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128-quant:int8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_8b-bench-bfloat16-input_output_len:128,128] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[llama_v3.2_1b-bench-bfloat16-input_output_len:512,32-quant:fp8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128+512,32-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-float16-input_output_len:128,128-loras:8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
-perf/test_perf.py::test_perf[mixtral_8x7b_v0.1-bench-streaming-float16-input_output_len:128,128-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5274894)
+perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:512,200-quant:fp8-tp:4] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-cppmanager-exe-plugin_ifb-float16-input_output_len:200,2000-reqs:64-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:1000,1000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-quant:fp8-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:20000,2000-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-bfloat16-maxbs:64-input_output_len:500,2000-quant:fp8-con:1] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:20000,2000-reqs:500-con:250] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_nemotron_nano_8b-bench-pytorch-bfloat16-maxbs:512-input_output_len:5000,500-reqs:500-con:250] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
+perf/test_perf.py::test_perf[llama_v3.1_70b_instruct-bench-bfloat16-input_output_len:200,2000-reqs:64-con:1-gpus:8] SKIP (https://nvbugspro.nvidia.com/bug/5304388)
 perf/test_perf.py::test_perf[llama_v3.1_8b-cppmanager-exe-plugin_ifb-bfloat16-mp-maxbs:256-input_output_len:128,128-pp:2] SKIP (https://nvbugspro.nvidia.com/bug/5295390)
 perf/test_perf.py::test_perf[llama_70b_sq_per_tensor-cppmanager-exe-plugin_ifb-float16-input_output_len:128,128+512,32-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5295390)
 perf/test_perf.py::test_perf[starcoder_15.5b-cppmanager-ootb_except_mha-float16-maxbs:1-input_output_len:512,200-reqs:10-gpus:4] SKIP (https://nvbugspro.nvidia.com/bug/5295390)