aarnphm-ec2-dev e4ac0ed8b7 fix(cuda): support loading in single GPU ...

add available_devices for getting # of available GPUs

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

2023-07-21 08:10:01 +00:00

..

_strategies

feat: GPTQ + vLLM and LlaMA (#113)

2023-07-19 18:12:12 -04:00

models

fix(cuda): support loading in single GPU

2023-07-21 08:10:01 +00:00

__init__.py

fix(tools): adhere to style guidelines (#31)

2023-06-18 20:03:17 -04:00

client_test.py

feat(test): snapshot testing (#107)

2023-07-10 17:23:19 -04:00

configuration_test.py

feat(llama): add default prompt for LlaMA-2 (#122)

2023-07-20 07:46:33 -04:00

conftest.py

fix(tests): skip running models tests on CI

2023-07-19 22:40:40 +00:00

llm_test.py

feat(test): snapshot testing (#107)

2023-07-10 17:23:19 -04:00

models_test.py

feat(llama): add default prompt for LlaMA-2 (#122)

2023-07-20 07:46:33 -04:00

package_test.py

fix(tests): mark package on CI to xfail

2023-07-15 12:48:28 +00:00

strategies_test.py

feat(llama): add default prompt for LlaMA-2 (#122)

2023-07-20 07:46:33 -04:00