From bca5e29387f2be2b75b7911c2e53c3611fbb01d4 Mon Sep 17 00:00:00 2001
From: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Date: Mon, 13 Oct 2025 11:14:24 +0800
Subject: [PATCH] [None][chore] Update constaintfor release (#8211)

Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
---
 tests/integration/defs/accuracy/test_cli_flow.py   |  1 +
 tests/integration/defs/accuracy/test_llm_api.py    |  2 ++
 .../defs/accuracy/test_llm_api_pytorch.py          | 14 ++++++++------
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/tests/integration/defs/accuracy/test_cli_flow.py b/tests/integration/defs/accuracy/test_cli_flow.py
index f5f55a4a35..e25bc5a3dc 100644
--- a/tests/integration/defs/accuracy/test_cli_flow.py
+++ b/tests/integration/defs/accuracy/test_cli_flow.py
@@ -210,6 +210,7 @@ class TestLlama3_3NemotronSuper49Bv1(CliFlowAccuracyTestHarness):
     EXAMPLE_FOLDER = "models/core/nemotron_nas"
 
     @pytest.mark.skip_less_device(2)
+    @pytest.mark.skip_less_device_memory(80000)
     def test_auto_dtype_tp2(self):
         self.run(tasks=[MMLU(self.MODEL_NAME)], tp_size=2, dtype='auto')
 
diff --git a/tests/integration/defs/accuracy/test_llm_api.py b/tests/integration/defs/accuracy/test_llm_api.py
index 8f97611519..e019572ada 100644
--- a/tests/integration/defs/accuracy/test_llm_api.py
+++ b/tests/integration/defs/accuracy/test_llm_api.py
@@ -289,6 +289,8 @@ class TestMixtral8x7BInstruct(LlmapiAccuracyTestHarness):
     MODEL_PATH = f"{llm_models_root()}/Mixtral-8x7B-Instruct-v0.1"
 
     @skip_post_blackwell
+    @pytest.mark.skip_less_device(2)
+    @pytest.mark.skip_less_device_memory(80000)
     def test_awq_tp2(self):
         quant_config = QuantConfig(quant_algo=QuantAlgo.W4A16_AWQ)
         with LLM(self.MODEL_PATH,
diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
index 4e4bd55f40..8e868ccb51 100644
--- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py
+++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
@@ -2401,9 +2401,10 @@ class TestLlama3_1NemotronNano8Bv1(LlmapiAccuracyTestHarness):
             task.evaluate(llm)
             task = GSM8K(self.MODEL_NAME)
             task.evaluate(llm)
-            task = GPQADiamond(self.MODEL_NAME)
-            task.evaluate(llm,
-                          extra_evaluator_kwargs=dict(apply_chat_template=True))
+            # skip gpqa test due to time consuming
+            # task = GPQADiamond(self.MODEL_NAME)
+            # task.evaluate(llm,
+            #               extra_evaluator_kwargs=dict(apply_chat_template=True))
 
     @skip_pre_hopper
     @pytest.mark.skip_device_not_contain(["H100", "B200"])
@@ -2415,9 +2416,10 @@ class TestLlama3_1NemotronNano8Bv1(LlmapiAccuracyTestHarness):
             task.evaluate(llm)
             task = GSM8K(self.MODEL_NAME)
             task.evaluate(llm)
-            task = GPQADiamond(self.MODEL_NAME)
-            task.evaluate(llm,
-                          extra_evaluator_kwargs=dict(apply_chat_template=True))
+            # skip gpqa test due to time consuming
+            # task = GPQADiamond(self.MODEL_NAME)
+            # task.evaluate(llm,
+            #               extra_evaluator_kwargs=dict(apply_chat_template=True))
 
 
 class TestNemotronUltra(LlmapiAccuracyTestHarness):