7f54b7336a
Update the Mixtral GPTQ test to use a model with `desc_act=true` and `group_size!=-1` to ensure that we are checking activation sorting/non-full K (with tensor parallelism). The `desc_act=false` case is already checked by the Mixtral AWQ test. |
||
---|---|---|
.. | ||
images | ||
models | ||
conftest.py | ||
poetry.lock | ||
pyproject.toml | ||
pytest.ini | ||
requirements.txt |