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

[None][fix] disable thread leak check for kimi (#10337)

Browse Source 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
This commit is contained in:
xinhe-nv 2025-12-31 14:31:37 +08:00 committed by GitHub
parent 6c1abf2d45
commit 1e9c153b4c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -2916,7 +2916,8 @@ class TestGLM4_6(LlmapiAccuracyTestHarness):
task.evaluate(llm)
@pytest.mark.timeout(7200)
@pytest.mark.threadleak(enabled=False)
@pytest.mark.timeout(10800)
@pytest.mark.skip_less_device_memory(100000)
class TestKimiK2(LlmapiAccuracyTestHarness):
MODEL_NAME = "moonshotai/Kimi-K2-Instruct"
@ -2960,7 +2961,6 @@ class TestKimiK2(LlmapiAccuracyTestHarness):
task.evaluate(llm)
@skip_pre_blackwell
@pytest.mark.timeout(7200)
@pytest.mark.skip_less_device_memory(120000)
@pytest.mark.parametrize("tp_size", [
pytest.param(4, marks=pytest.mark.skip_less_device(4)),