avoid cudaFree overlap with cuda graph

Signed-off-by: Chuang Zhu <[email protected]>

Author: chuangz0

tensorrt_llm/_torch/pyexecutor/py_executor_creator.py

@@ -1,5 +1,6 @@
 import copy
 import enum
+import gc
 import importlib
 import os
 from concurrent.futures import ThreadPoolExecutor
@@ -600,6 +601,8 @@ def drafting_loop_wrapper(model):
     with mem_monitor.observe_creation_stage(
             _ExecutorCreationStage.INIT_EXTRA_RESOURCES
             if estimating_kv_cache else _ExecutorCreationStage.EXTRA_RESOURCES):
+        # run gc.collect() to free memory of the previous py_executor, avoid cudaFree overlap with cuda graph capture
+        gc.collect()
         py_executor = create_py_executor_instance(
             dist=dist,
             resources=resources,

tests/integration/test_lists/waives.txt

@@ -355,10 +355,6 @@ triton_server/test_triton_llm.py::test_mistral_small_3_1_24b_pixtral[TYPE_FP16-T
 triton_server/test_triton_llm.py::test_mistral_small_3_1_24b_pixtral[TYPE_FP16-TYPE_BF16-False-1---False-True-False-0-1-enableDecoupleMode-inflight_fused_batching-disableTrtOverlap--0.7-max_utilization---1-1-1-False-tensorrt_llm_bls] SKIP (https://nvbugs/5606136)
 accuracy/test_cli_flow.py::TestMinitron4BBase::test_fp8 SKIP (https://nvbugs/5606233)
 examples/test_gpt.py::test_llm_minitron_fp8_with_pseudo_loras[4b] SKIP (https://nvbugs/5606233)
-disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_deepseek[True-False-DeepSeek-V3-Lite-fp8/fp8] SKIP (https://nvbugs/5626197)
-disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_deepseek[True-True-DeepSeek-V3-Lite-fp8/fp8] SKIP (https://nvbugs/5628952)
 cpp/test_e2e.py::test_benchmarks[t5-90] SKIP (https://nvbugs/5630196)
 accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4_4gpus[latency_moe_trtllm_eagle3] SKIP (https://nvbugs/5630700)
-accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_nixl_backend SKIP (https://nvbugs/5628952)
-accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_guided_decoding[xgrammar-mtp_nextn=2] SKIP (https://nvbugs/5628952)
 full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype SKIP (https://nvbugs/5569696)