Skip to content

Commit c4d4590

Browse files
committed
fix invalid test name
Signed-off-by: Ivy Zhang <[email protected]>
1 parent b957ac4 commit c4d4590

File tree

4 files changed

+20
-20
lines changed

4 files changed

+20
-20
lines changed

tests/integration/defs/accuracy/test_llm_api_pytorch.py

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -695,24 +695,24 @@ def test_auto_dtype(self):
695695

696696
class TestMistralSmall24B(LlmapiAccuracyTestHarness):
697697
MODEL_NAME = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
698+
MODEL_PATH = f"{llm_models_root()}/Mistral-Small-3.1-24B-Instruct-2503"
698699

699700
@pytest.mark.skip_less_device_memory(80000)
700-
@pytest.mark.parametrize(
701-
"model_path, expected_quant_algo",
702-
[
703-
# Original bfloat16 model.
704-
(f"{llm_models_root()}/Mistral-Small-3.1-24B-Instruct-2503", None),
705-
# FP8 model.
706-
pytest.param(
707-
f"{llm_models_root()}/Mistral-Small-3.1-24B-Instruct-2503-fp8",
708-
QuantAlgo.FP8,
709-
marks=skip_pre_ada,
710-
),
711-
],
712-
)
713-
def test_auto_dtype(self, model_path, expected_quant_algo):
701+
def test_auto_dtype(self):
702+
with LLM(self.MODEL_PATH) as llm:
703+
task = CnnDailymail(self.MODEL_NAME)
704+
task.evaluate(llm)
705+
task = MMLU(self.MODEL_NAME)
706+
task.evaluate(llm)
707+
task = GSM8K(self.MODEL_NAME)
708+
task.evaluate(llm)
709+
710+
@skip_pre_ada
711+
@pytest.mark.skip_less_device_memory(80000)
712+
def test_fp8(self):
713+
model_path = f"{llm_models_root()}/Mistral-Small-3.1-24B-Instruct-2503-fp8"
714714
with LLM(model_path) as llm:
715-
assert llm.args.quant_config.quant_algo == expected_quant_algo
715+
assert llm.args.quant_config.quant_algo == QuantAlgo.FP8
716716
task = CnnDailymail(self.MODEL_NAME)
717717
task.evaluate(llm)
718718
task = MMLU(self.MODEL_NAME)

tests/integration/test_lists/qa/llm_function_full.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -454,8 +454,8 @@ accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[
454454
accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[eagle3_one_model=False]
455455
accuracy/test_llm_api_pytorch.py::TestMistral7B::test_auto_dtype
456456
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype
457-
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype[/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503-None]
458-
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype[/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503-fp8-FP8]
457+
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype
458+
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_fp8
459459
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_auto_dtype[tp8-cuda_graph=False]
460460
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_auto_dtype[tp8ep4-cuda_graph=True]
461461
accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_auto_dtype[tp8ep8-cuda_graph=True]

tests/integration/test_lists/qa/llm_function_sanity.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus_online
4646
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus_online_eplb[fp8kv=False]
4747
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus_online_eplb[fp8kv=True]
4848
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype
49-
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype[/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503-None]
49+
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype
5050
accuracy/test_llm_api_pytorch.py::TestKanana_Instruct::test_auto_dtype
5151
accuracy/test_llm_api_pytorch.py::TestKimiK2::test_fp8_blockscale[latency]
5252
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4

tests/integration/test_lists/test-db/l0_h100.yml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -205,8 +205,8 @@ l0_h100:
205205
- accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_fp8_prequantized
206206
- accuracy/test_llm_api_pytorch.py::TestGemma3_27BInstruct::test_fp8_prequantized
207207
- accuracy/test_llm_api_pytorch.py::TestGemma3_27BInstruct::test_auto_dtype
208-
- accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype[/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503-None]
209-
- accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype[/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503-fp8-FP8]
208+
- accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype
209+
- accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_fp8
210210
- accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8_block_scales[latency-torch_compile=False]
211211
- accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8_block_scales[latency-torch_compile=True]
212212
- accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding[llguidance]

0 commit comments

Comments
 (0)