[https://nvbugs/5766986][fix] fixed the shard_all_unprocessed default value to align with the default.yml (#10271)

Signed-off-by: Eran Geva <[email protected]>

Author: MrGeva

tensorrt_llm/_torch/auto_deploy/transform/library/sharding.py

@@ -136,7 +136,7 @@ class ShardingTransformConfig(TransformConfig):
         default_factory=lambda: [ShardingDim.TP, ShardingDim.EP, ShardingDim.BMM]
     )
     shard_all_unprocessed: bool = Field(
-        default=False,
+        default=True,
         description="When True, apply simple shard (column split + all_gather) to "
         "'leftover' linear nodes that are not part of any layer subgraph.",
     )

tests/integration/test_lists/waives.txt

@@ -496,16 +496,6 @@ disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backen
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen] SKIP (https://nvbugs/5715568)
 unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741)
 unittest/executor/test_rpc_worker.py SKIP (https://nvbugs/5605741)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_dist_backend.py::test_dist_backend_all_gather[torch] SKIP (https://nvbugs/5766986)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_dist_backend.py::test_dist_backend_all_gather[trtllm] SKIP (https://nvbugs/5766986)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-False-False-2] SKIP (https://nvbugs/5766982)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-False-True-2] SKIP (https://nvbugs/5766982)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-True-False-2] SKIP (https://nvbugs/5766982)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-True-True-2] SKIP (https://nvbugs/5766982)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-False-False-8] SKIP (https://nvbugs/5766974)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-False-True-8] SKIP (https://nvbugs/5766974)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-True-False-8] SKIP (https://nvbugs/5766974)
-unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-True-True-8] SKIP (https://nvbugs/5766974)
 triton_server/test_triton.py::test_gpt_gather_logits[gpt-gather-logits] SKIP (https://nvbugs/5766960)
 stress_test/stress_test.py::test_run_stress_test[llama-v3-8b-instruct-hf_tp1-stress_time_300s_timeout_450s-GUARANTEED_NO_EVICT-pytorch-stress-test] SKIP (https://nvbugs/5766952)
 accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[tp4ep4_cudagraph_overlap] SKIP (https://nvbugs/5722618)