vllm/lora at 72d3a30c6327e70de3595d00f04e2d577fcbbb68 - vllm

Files

Kunshang Ji 96b6f475dd Remove hardcoded device="cuda" to support more devices (#2503 )

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

2024-02-01 15:46:39 -08:00

__init__.py

2024-01-23 15:26:37 -08:00

conftest.py

2024-02-01 15:46:39 -08:00

test_layers.py

2024-02-01 15:46:39 -08:00

test_llama.py

2024-01-23 15:26:37 -08:00

test_lora_manager.py

2024-01-23 15:26:37 -08:00

test_lora.py

2024-01-23 15:26:37 -08:00

test_punica.py

2024-01-23 15:26:37 -08:00

test_tokenizer.py

2024-01-23 15:26:37 -08:00

test_utils.py

2024-01-23 15:26:37 -08:00

test_worker.py

2024-02-01 15:46:39 -08:00

utils.py

2024-01-23 15:26:37 -08:00