AlpinDale cda0e93a10 abstract away the platform for device capability vor 7 Monaten
..
__init__.py 2bd6c92f73 fix: lora inclusion in wheels vor 1 Jahr
fully_sharded_layers.py 8a6e83b52e feat: fully sharded QKVParallelLinearWithLora support vor 7 Monaten
layers.py 0f4a9ee77b quantized lm_head (#582) vor 7 Monaten
lora.py 56e0b8223c chore: add base class for LoRA-supported models vor 7 Monaten
models.py 0a6db357d8 fix: use safetensor keys instead of adapter_config.json to find unexpected modules vor 7 Monaten
punica.py cda0e93a10 abstract away the platform for device capability vor 7 Monaten
request.py 5b0c11d190 support pipeline parallel pynccl groups vor 7 Monaten
utils.py 8a6e83b52e feat: fully sharded QKVParallelLinearWithLora support vor 7 Monaten
worker_manager.py 25feb1d592 chore: add support for pinning lora adapters in the lru cache vor 7 Monaten