test: waive failed cases (#6394)

Signed-off-by: Xin He (SW-GPU) <[email protected]>

Author: xinhe-nv

tests/integration/defs/accuracy/test_llm_api_pytorch.py

@@ -367,9 +367,11 @@ def test_auto_dtype_tp8(self):
     @skip_pre_hopper
     def test_fp8_tp4(self):
         model_path = f"{llm_models_root()}/modelopt-hf-model-hub/Llama-3.3-70B-Instruct-fp8"
-        kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.6)
+        kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.5)
         with LLM(model_path,
                  tensor_parallel_size=4,
+                 max_seq_len=8192,
+                 max_batch_size=32,
                  kv_cache_config=kv_cache_config) as llm:
             assert llm.args.quant_config.quant_algo == QuantAlgo.FP8
             task = MMLU(self.MODEL_NAME)

tests/integration/test_lists/waives.txt

@@ -442,3 +442,10 @@ unittest/trt/attention/test_gpt_attention.py -k "partition3" SKIP (https://nvbug
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image-False] SKIP (https://nvbugs/5414909)
 unittest/_torch/multi_gpu_modeling/test_llama4.py::test_llama4[pp1-ep1-disable_adp-enable_graph-tp8-trtllm-scout] SKIP (https://nvbugs/5418673)
 unittest/_torch/multi_gpu_modeling/test_llama4.py::test_llama4[pp1-ep4-enable_adp-enable_graph-tp8-trtllm-scout] SKIP (https://nvbugs/5418673)
+examples/test_llama.py::test_llm_api_lookahead_decoding_1gpu[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct] SKIP (https://nvbugs/5419066)
+examples/test_multimodal.py::test_llm_multimodal_general[fuyu-8b-pp:1-tp:1-float16-bs:8-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5360086)
+examples/test_multimodal.py::test_llm_multimodal_general[kosmos-2-pp:1-tp:1-float16-bs:8-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5141288)
+examples/test_qwen.py::test_llm_qwen_7b_int8_kv_1node_1gpus[qwen2_vl_7b_instruct-enable_gemm_plugin-enable_weight_only] SKIP (https://nvbugs/5419067)
+examples/test_qwen.py::test_llm_qwen_awq_single_gpu_summary[qwen2_vl_7b_instruct-nb:4] SKIP (https://nvbugs/5419068)
+examples/test_qwen.py::test_llm_qwen_smooth_quant_single_gpu_summary[qwen2_vl_7b_instruct-enable_ptpc-nb:4] SKIP (https://nvbugs/5419069)
+examples/test_recurrentgemma.py::test_llm_recurrentgemma_1gpu[use_cpp_session-recurrentgemma-2b-use_paged_cache-fp8-float16-enable_attn_plugin-enable_gemm_plugin] SKIP (https://nvbugs/5419070)