diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index c33aabcddc..99bbbd59cb 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -308,7 +308,7 @@ class TestLlama3_2_1B(LlmapiAccuracyTestHarness): task.evaluate(llm) def test_fp8_prequantized(self): - model_path = f"{llm_models_root()}/ llama-3.2-models/Llama-3.2-1B-FP8" + model_path = f"{llm_models_root()}/llama-3.2-models/Llama-3.2-1B-FP8" with LLM(model_path) as llm: assert llm.args.quant_config.quant_algo == QuantAlgo.FP8 assert llm.args.quant_config.kv_cache_quant_algo == QuantAlgo.FP8 diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 861b5d9d62..f794525f84 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -432,7 +432,7 @@ full:B200/accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[late full:B200/accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_trtllm] SKIP (https://nvbugs/5355219) examples/test_llama.py::test_llm_llama_lookahead_xqa_fp8_1gpu[llama-3.1-8b] SKIP (https://nvbugs/5355054) examples/test_llama.py::test_llm_llama_lookahead_xqa_fp8_1gpu[llama-3.2-1b] SKIP (https://nvbugs/5355054) -examples/test_multimodal.py::test_llm_multimodal_general[nougat-base-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5354936) +examples/test_multimodal.py::test_llm_multimodal_general[nougat-base-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5354825) examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:8-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5360086) examples/test_phi.py::test_llm_phi_quantization_1gpu[Phi-3.5-mini-instruct-fp8-float16] SKIP (https://nvbugs/5355054) accuracy/test_cli_flow.py::TestLlama3_8BInstruct::test_fp8 SKIP (https://nvbugs/5355054) @@ -440,3 +440,6 @@ accuracy/test_cli_flow.py::TestLlama3_1_8BInstruct::test_fp8_prequantized SKIP ( accuracy/test_cli_flow.py::TestLlama3_1_8BInstruct::test_medusa_fp8_prequantized SKIP (https://nvbugs/5355054) examples/test_gpt.py::test_starcoder_fp8_quantization_2gpu[starcoder] SKIP (https://nvbugs/5355128) examples/test_gpt.py::test_starcoder_fp8_quantization_2gpu[starcoderplus] SKIP (https://nvbugs/5355128) +examples/test_multimodal.py::test_llm_multimodal_general[fuyu-8b-pp:1-tp:1-float16-bs:8-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5360086) +examples/test_multimodal.py::test_llm_multimodal_general[llava-1.5-7b-hf-pp:1-tp:1-float16-bs:8-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5360086) +test_e2e.py::test_ptp_scaffolding[DeepSeek-R1-Distill-Qwen-7B-DeepSeek-R1/DeepSeek-R1-Distill-Qwen-7B] SKIP (https://nvbugs/5365714)