diff --git a/tests/integration/defs/accuracy/references/gsm8k.yaml b/tests/integration/defs/accuracy/references/gsm8k.yaml index ef32f74f1ba0..118bf564ef66 100644 --- a/tests/integration/defs/accuracy/references/gsm8k.yaml +++ b/tests/integration/defs/accuracy/references/gsm8k.yaml @@ -293,8 +293,6 @@ nvidia/Llama-3_1-Nemotron-Ultra-253B-v1: - quant_algo: FP8 kv_cache_quant_algo: FP8 accuracy: 94.16 -kanana-1.5-2.1b-instruct-2505: - - accuracy: 75.81 google/gemma-3-1b-it: - accuracy: 25.52 # score getting from lm-eval with HF implementation - quant_algo: FP8 diff --git a/tests/integration/defs/accuracy/references/mmlu.yaml b/tests/integration/defs/accuracy/references/mmlu.yaml index a870fbba6402..a5c473d08c17 100644 --- a/tests/integration/defs/accuracy/references/mmlu.yaml +++ b/tests/integration/defs/accuracy/references/mmlu.yaml @@ -334,8 +334,6 @@ nvidia/Llama-3_1-Nemotron-Ultra-253B-v1: - quant_algo: FP8 kv_cache_quant_algo: FP8 accuracy: 83.36 -kanana-1.5-2.1b-instruct-2505: - - accuracy: 56.89 mistralai/Ministral-8B-Instruct-2410: - accuracy: 66.35 - quant_algo: FP8 diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index f0a089120b1d..1852e2987a0b 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -5152,23 +5152,6 @@ def test_auto_dtype(self): task.evaluate(llm) -class TestKanana_Instruct(LlmapiAccuracyTestHarness): - MODEL_NAME = "kanana-1.5-2.1b-instruct-2505" - MODEL_PATH = f"{llm_models_root()}/kanana-1.5-2.1b-instruct-2505" - - @pytest.mark.skip_device_not_contain(["H20", "H100"]) - def test_auto_dtype(self): - "RCCA: https://nvbugspro.nvidia.com/bug/5310520" - pytorch_config = dict(cuda_graph_config=CudaGraphConfig( - enable_padding=True, max_batch_size=384)) - with LLM(self.MODEL_PATH, **pytorch_config, - enable_attention_dp=True) as llm: - task = MMLU(self.MODEL_NAME) - task.evaluate(llm) - task = GSM8K(self.MODEL_NAME) - task.evaluate(llm) - - @skip_pre_hopper @pytest.mark.skip_less_device_memory(80000) class TestGPTOSS(LlmapiAccuracyTestHarness): diff --git a/tests/integration/defs/perf/_model_paths.py b/tests/integration/defs/perf/_model_paths.py index 522e9eb87dc2..74357e5a4065 100644 --- a/tests/integration/defs/perf/_model_paths.py +++ b/tests/integration/defs/perf/_model_paths.py @@ -65,7 +65,6 @@ "phi_4_multimodal_instruct": "multimodals/Phi-4-multimodal-instruct", "phi_4_multimodal_instruct_fp4": "multimodals/Phi-4-multimodal-instruct-FP4", "phi_4_multimodal_instruct_fp8": "multimodals/Phi-4-multimodal-instruct-FP8", - "bielik_11b_v2.2_instruct": "Bielik-11B-v2.2-Instruct", "gpt_oss_120b_fp4": "gpt_oss/gpt-oss-120b", "gpt_oss_20b_fp4": "gpt_oss/gpt-oss-20b", "gpt_oss_120b_eagle3": "gpt_oss/gpt-oss-120b", diff --git a/tests/integration/test_lists/qa/llm_function_core.txt b/tests/integration/test_lists/qa/llm_function_core.txt index 9fde8bb9d1fa..203ae6382303 100644 --- a/tests/integration/test_lists/qa/llm_function_core.txt +++ b/tests/integration/test_lists/qa/llm_function_core.txt @@ -538,7 +538,6 @@ accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[trtllm-aut accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[trtllm-fp8] accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-auto] accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-fp8] -accuracy/test_llm_api_pytorch.py::TestKanana_Instruct::test_auto_dtype accuracy/test_llm_api_pytorch.py::TestKimiK25::test_nvfp4[dep8] accuracy/test_llm_api_pytorch.py::TestKimiK25::test_nvfp4[ep8] accuracy/test_llm_api_pytorch.py::TestKimiK25::test_nvfp4[tp8] diff --git a/tests/integration/test_lists/test-db/l0_perf.yml b/tests/integration/test_lists/test-db/l0_perf.yml index 5bc5a05c45df..db569674c60d 100644 --- a/tests/integration/test_lists/test-db/l0_perf.yml +++ b/tests/integration/test_lists/test-db/l0_perf.yml @@ -14,18 +14,3 @@ l0_perf: backend: pytorch tests: - perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-pytorch-float16-input_output_len:128,128-reqs:8192] - - - condition: - ranges: - system_gpu_count: - gte: 1 - lte: 1 - wildcards: - gpu: - - '*l40s*' - linux_distribution_name: ubuntu* - terms: - stage: pre_merge - backend: pytorch - tests: - - perf/test_perf.py::test_perf[bielik_11b_v2.2_instruct-bench-pytorch-bfloat16-input_output_len:128,128] diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index b2971766eacd..b498dd50c86f 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -72,7 +72,6 @@ accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-cutl accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-cutlass-auto] SKIP (https://nvbugs/5596343) accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-tp4-cutlass-auto] SKIP (https://nvbugs/5596343) accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[cutlass-auto] SKIP (https://nvbugs/5596343) -accuracy/test_llm_api_pytorch.py::TestKanana_Instruct::test_auto_dtype SKIP (https://nvbugs/6209806) accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/6490043) accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=FLASHINFER-torch_compile=True] SKIP (https://nvbugs/6422337) accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp4-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/5616182) diff --git a/tests/unittest/llmapi/test_llm_pytorch.py b/tests/unittest/llmapi/test_llm_pytorch.py index 3b09da755896..bce68e10531e 100644 --- a/tests/unittest/llmapi/test_llm_pytorch.py +++ b/tests/unittest/llmapi/test_llm_pytorch.py @@ -726,59 +726,6 @@ def test_llama_3_3_70b_fp8_with_squad_lora_tp2() -> None: llm.shutdown() -@skip_gpu_memory_less_than_80gb -@pytest.mark.part2 -@test_lora_with_and_without_cuda_graph -def test_bielik_11b_v2_2_instruct_multi_lora(cuda_graph_config) -> None: - model_dir = f"{llm_models_root()}/Bielik-11B-v2.2-Instruct" - - target_modules = ['attn_q', 'attn_k', 'attn_v'] - - # Set up temporary directory for LoRA adapters - with tempfile.TemporaryDirectory() as lora_dir: - print("Creating dummy LoRAs...") - - model = AutoModelForCausalLM.from_pretrained(model_dir, - dtype=torch.bfloat16, - device_map="auto") - hf_modules = ["q_proj", "k_proj", "v_proj"] - peft_lora_config = PeftLoraConfig(r=8, - target_modules=hf_modules, - bias="none", - task_type="CAUSAL_LM") - lora_paths = [] - for i in range(2): - lora_model = get_peft_model(model, peft_lora_config) - for param in lora_model.parameters(): - param.data.zero_() - lora_path = f"{lora_dir}/lora_{i}" - lora_model.save_pretrained(lora_path) - lora_paths.append(lora_path) - - trtllm_lora_config = LoraConfig(lora_target_modules=target_modules, - max_lora_rank=8, - max_loras=2, - max_cpu_loras=2) - llm = LLM(model_dir, - lora_config=trtllm_lora_config, - cuda_graph_config=cuda_graph_config) - - prompts = [ - "Kim był Mikołaj Kopernik i z czego zasłynął?", - "Gdzie znajduje się stolica Polski?", - ] - lora_req1 = LoRARequest("lora-1", 0, lora_paths[0]) - lora_req2 = LoRARequest("lora-2", 1, lora_paths[1]) - lora_requests = [lora_req1, lora_req2] - sampling_params = SamplingParams(max_tokens=200) - - outputs = llm.generate(prompts, - sampling_params, - lora_request=lora_requests) - - assert len(outputs) == 2 - - @pytest.mark.part2 @test_lora_with_and_without_cuda_graph def test_gemma3_1b_instruct_multi_lora(cuda_graph_config) -> None: