From cad19eeea087caf7a5af30fe345dea5a3a458ccc Mon Sep 17 00:00:00 2001 From: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com> Date: Wed, 15 Jul 2026 02:44:08 -0700 Subject: [PATCH 1/2] [nvbugs/6426847][fix] Guard MpiPoolSession isinstance against monkey-patch The session-reuse test infrastructure (tests/test_common/session_reuse.py) monkey-patches MpiPoolSession in tensorrt_llm.executor.proxy with a factory function to enable pool reuse across LLM instances. This broke isinstance(self.mpi_session, MpiPoolSession) in _start_executor_workers with TypeError: isinstance() arg 2 must be a type, a tuple of types, or a union. Switch to a negative check against the never-patched MpiCommSession / RemoteMpiCommSessionClient types, matching the pattern already used earlier in the same function. Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com> --- tensorrt_llm/executor/proxy.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tensorrt_llm/executor/proxy.py b/tensorrt_llm/executor/proxy.py index 11451bad5b67..4c2482304a5e 100644 --- a/tensorrt_llm/executor/proxy.py +++ b/tensorrt_llm/executor/proxy.py @@ -573,7 +573,9 @@ def mpi_done_callback(future: concurrent.futures.Future): raise RuntimeError( "Executor worker returned error") from ready_signal - if isinstance(self.mpi_session, MpiPoolSession) and len(status) == 3: + if not isinstance( + self.mpi_session, + (MpiCommSession, RemoteMpiCommSessionClient)) and len(status) == 3: worker_process_identities: List[WorkerProcessIdentity] = status[2] self._worker_process_monitor.register(worker_process_identities) From 333a4fb7c1d8200aa6dde6b3e5a6f112a580f36a Mon Sep 17 00:00:00 2001 From: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com> Date: Wed, 15 Jul 2026 05:14:05 -0700 Subject: [PATCH 2/2] [nvbugs/6426847][chore] Remove stale waiver after fix Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com> --- tests/integration/test_lists/waives.txt | 3 --- 1 file changed, 3 deletions(-) diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index bfc89046facd..bc7cc97396cb 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -37,7 +37,6 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0- accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=True-cuda_graph=False-overlap_scheduler=False-torch_compile=True-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6305404) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6412102) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6388129) -accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6426847) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/6445456) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True] SKIP (https://nvbugs/6402058) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[pp4-mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/6278337) @@ -434,9 +433,7 @@ test_e2e.py::test_multi_nodes_eval[MiniMax-M2-tp16-mmlu] SKIP (https://nvbugs/63 test_e2e.py::test_multi_nodes_eval[MiniMax-M3-tp16-mmlu] SKIP (https://nvbugs/6373561) test_e2e.py::test_ptp_quickstart_advanced_deepseek_r1_w4afp8_8gpus[DeepSeek-R1-W4AFP8-DeepSeek-R1/DeepSeek-R1-W4AFP8] SKIP (https://nvbugs/5836830) unittest/_torch/misc/test_share_tensor.py::TestShareTensor::test_share_tensor_different_dtypes SKIP (https://nvbugs/6418021) -unittest/_torch/modeling -k "modeling_out_of_tree" SKIP (https://nvbugs/6426847) unittest/_torch/modeling -k "modeling_qwen" SKIP (https://nvbugs/6433376) -unittest/_torch/modeling/test_modeling_out_of_tree.py::TestOutOfTree::test_llm_api[True] SKIP (https://nvbugs/6426847) unittest/_torch/modeling/test_modeling_qwen3_5_vl.py::test_qwen35_dense_vl_resolves_mamba_ssm_cache_dtype SKIP (https://nvbugs/6433376) unittest/_torch/modules/moe/test_moe_backend.py::test_moe_backend[act=Relu2-e60_k4_h2048_i1408-seq=8-dtype=torch.bfloat16-backend=TRTLLM-quant=NVFP4-routing=Renormalize] SKIP (https://nvbugs/5989912) unittest/_torch/modules/tests_lora_modules/test_nemotron_h_lora_sanity.py::TestNemotronHLoRA::test_lora_pp2_sanity SKIP (https://nvbugs/6428124)