mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
4c7191af67
* Move TRT-LLM backend repo to TRT-LLM repo Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * Address review comments Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * debug ci Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * Update triton backend Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * Fixes after update Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> --------- Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
13 lines
680 B
INI
13 lines
680 B
INI
[pytest]
|
|
threadleak = True
|
|
threadleak_exclude = asyncio_\d+
|
|
junit_family=legacy
|
|
addopts = --ignore-glob="*perf/test_perf.py" --ignore-glob="*test_list_validation.py" --ignore-glob="*llm-test-workspace*" --durations=0 -W ignore::DeprecationWarning
|
|
norecursedirs = ./triton/perf
|
|
markers =
|
|
skip_less_device: skip when less device detected than the declared
|
|
skip_less_device_memory: skip when less device memory detected than the requested
|
|
skip_less_host_memory: skip when less host memory detected than the requested
|
|
support_fp8: skip when fp8 is not supported on the device
|
|
skip_device_not_contain: skip when the device does not contain the specified keyword
|