From 49e3c7e57b62d0d82f9235367ceb6b9dd047b8c3 Mon Sep 17 00:00:00 2001 From: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com> Date: Sun, 7 Jun 2026 23:39:01 -0700 Subject: [PATCH] [None][fix] Fix and unwaive nemotron related bugs Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com> --- tests/integration/defs/accuracy/test_llm_api_pytorch.py | 1 + tests/integration/test_lists/waives.txt | 4 ---- tests/unittest/llmapi/test_llm_pytorch.py | 3 ++- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index a56816ea4832..4eef0dc1d6ca 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -4091,6 +4091,7 @@ def test_auto_dtype_tp8(self): with LLM(self.MODEL_PATH, tensor_parallel_size=8, kv_cache_config=kv_cache_config, + trust_remote_code=True, **pytorch_config) as llm: task = CnnDailymail(self.MODEL_NAME) diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 755d80e69be7..d03746145437 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -128,8 +128,6 @@ accuracy/test_llm_api_pytorch.py::TestMiniMaxM2::test_4gpus[attention_dp=False-c accuracy/test_llm_api_pytorch.py::TestMistralLarge3_675B::test_fp8[latency_moe_deepgemm] SKIP (https://nvbugs/6163033) accuracy/test_llm_api_pytorch.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm] SKIP (https://nvbugs/6248827) accuracy/test_llm_api_pytorch.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm_eagle] SKIP (https://nvbugs/6157892) -accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8 SKIP (https://nvbugs/6244727) -accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_nvfp4_8gpus_mtp SKIP (https://nvbugs/6211693) accuracy/test_llm_api_pytorch.py::TestPhi4MiniInstruct::test_auto_dtype SKIP (https://nvbugs/6076767) accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[tp4ep4_cudagraph_overlap_adp_off] SKIP (https://nvbugs/6255417) accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[tp4ep4_cudagraph_overlap_adp_on] SKIP (https://nvbugs/6094068) @@ -415,8 +413,6 @@ unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741) unittest/executor/test_rpc_worker.py SKIP (https://nvbugs/5605741) unittest/llmapi/test_llm_multi_gpu.py -m "gpu4 and part0" SKIP (https://nvbugs/5348958) unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_phi3_lora_fused_modules_output_on_tp2_identical_to_tp1 SKIP (https://nvbugs/6109745) -unittest/llmapi/test_llm_pytorch.py::test_nemotron_nas_lora[None] SKIP (https://nvbugs/6248776) -unittest/llmapi/test_llm_pytorch.py::test_nemotron_nas_lora[cuda_graph_config0] SKIP (https://nvbugs/6248776) unittest/llmapi/test_memory_profiling.py::test_profile_kvcache SKIP (https://nvbugs/5580781) unittest/tools/test_layer_wise_benchmarks.py::test_performance_alignment[1] SKIP (https://nvbugs/6127669) unittest/tools/test_layer_wise_benchmarks.py::test_qwen3_next_gen_tep[1] SKIP (https://nvbugs/6153575) diff --git a/tests/unittest/llmapi/test_llm_pytorch.py b/tests/unittest/llmapi/test_llm_pytorch.py index 53b64a972898..ece8990f955c 100644 --- a/tests/unittest/llmapi/test_llm_pytorch.py +++ b/tests/unittest/llmapi/test_llm_pytorch.py @@ -610,7 +610,8 @@ def test_nemotron_nas_lora(cuda_graph_config) -> None: model= f"{llm_models_root()}/nemotron-nas/Llama-3_3-Nemotron-Super-49B-v1", lora_config=lora_config, - cuda_graph_config=cuda_graph_config) + cuda_graph_config=cuda_graph_config, + trust_remote_code=True) prompts = [ "Hello, how are you?",