mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
d0eb47d33a
* refactoring the multimodal input prep Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * adding out-of-tree override option Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * adding exceptional case for llava-next Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * fixing typo Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * addressing review comments, adding placement option, handling tokenizer variations Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * addressing pytest-asyncio behavior change Signed-off-by: Rakib Hasan <rhasan@nvidia.com> --------- Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
14 lines
724 B
INI
14 lines
724 B
INI
[pytest]
|
|
asyncio_default_fixture_loop_scope = module
|
|
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
|