kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[https://nvbugs/5769890][fix] Import get_free_port. (#10341)

Browse Source 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
This commit is contained in:
Yuxian Qiu 2025-12-31 09:47:27 +08:00 committed by GitHub
parent 74832a1895
commit ec8a388c25
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/defs/disaggregated/test_disaggregated.py
View File

@ -36,7 +36,7 @@ from defs.trt_test_alternative import check_call, check_output, popen
from test_common.perf_metrics_utils import (get_timing_metrics,
validate_timing_metrics)
from tensorrt_llm._utils import mpi_disabled
from tensorrt_llm._utils import get_free_port, mpi_disabled
from tensorrt_llm.logger import logger

4
tests/integration/test_lists/waives.txt
View File

@ -492,7 +492,6 @@ unittest/_torch/sampler/test_return_logits.py SKIP (https://nvbugs/5764627)
examples/serve/test_serve.py::test_config_file_loading[--config] SKIP (https://nvbugs/5754977)
full:RTXPro6000D/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=2-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/5740075)
examples/test_ray.py::test_ray_disaggregated_serving[tp2] SKIP (https://nvbugs/5612502)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf] SKIP (https://nvbugs/5748683)
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)
@ -503,8 +502,6 @@ full:sm89/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ngram SKIP (https://nvbugs/5768068)
test_e2e.py::test_eagle3_output_consistency_4gpus[Qwen3/saved_models_Qwen3-235B-A22B_fp8_hf-Qwen3/qwen3-235B-eagle3] SKIP (https://nvbugs/5685010)
examples/test_mistral.py::test_mistral_with_bf16_lora_torch[mistral-7b-v0.1] SKIP (https://nvbugs/5769855)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-3.1-8b-instruct-hf-fp8] SKIP (https://nvbugs/5769890)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/5769890)
accuracy/test_llm_api_pytorch_multimodal.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm] SKIP (TBD)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm-fp8] SKIP (https://nvbugs/5772396)
full:sm100/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm-auto] SKIP (https://nvbugs/5772396)
@ -516,7 +513,6 @@ accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_gather_generation_logits
test_e2e.py::test_eagle3_output_consistency_4gpus[Qwen3/Qwen3-30B-A3B-Qwen3/Qwen3-30B-eagle3] SKIP (https://nvbugs/5685010)
full:sm89/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_tp_pp_symmetric[GSM8K-tp2pp2] SKIP (https://nvbugs/5773047)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[enable_configurable_moe-dp4-trtllm-fp8] SKIP (https://nvbugs/5773201)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5769890)
unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[GQA_Block-torch_dist_all_reduce-True-False-2] SKIP (https://nvbugs/5766982)
test_e2e.py::test_ptp_quickstart_multimodal_kv_cache_reuse[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-0.6-image] SKIP (https://nvbugs/5773195)
accuracy/test_cli_flow.py::TestVicuna7B::test_eagle_2[cuda_graph=True-chunked_context=True] SKIP (https://nvbugs/5773185)