diff --git a/examples/auto_deploy/model_registry/configs/qwen3.5_moe_35b.yaml b/examples/auto_deploy/model_registry/configs/qwen3.5_moe_35b.yaml index 46498142a957..3ed30967a715 100644 --- a/examples/auto_deploy/model_registry/configs/qwen3.5_moe_35b.yaml +++ b/examples/auto_deploy/model_registry/configs/qwen3.5_moe_35b.yaml @@ -44,11 +44,14 @@ transforms: # "shared_expert_down_proj": "rowwise" # gating layer should be replicated as well # "gate": "gather" + compile_model: + # https://github.com/NVIDIA/TensorRT-LLM/issues/13858 + piecewise_enabled: false multi_stream_moe: stage: compile - enabled: true + enabled: false # https://github.com/NVIDIA/TensorRT-LLM/issues/12954 multi_stream_gemm: stage: compile - enabled: true + enabled: false # https://github.com/NVIDIA/TensorRT-LLM/issues/12954 gather_logits_before_lm_head: enabled: true diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 6dc4776bb633..5e5a0a2da902 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -21,7 +21,6 @@ accuracy/test_disaggregated_serving.py::TestQwen3_30B_A3B::test_mixed_ctx_gen_mo accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_fp8] SKIP (https://nvbugs/6478692) accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[nvfp4-4-attn_dp_off-trtllm] SKIP (https://nvbugs/6367792) accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[nvfp4_ws8_80gb-trtllm] SKIP (https://nvbugs/6450341) -accuracy/test_llm_api_autodeploy.py::TestQwen3_5_397B_MoE::test_bf16_small[4] SKIP (https://nvbugs/6507114) accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput_mtp] SKIP (https://nvbugs/6428101) accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput_mtp_trtllm] SKIP (https://nvbugs/6426868) accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[throughput_pp4_mtp] SKIP (https://nvbugs/6481323)