.. |
ops
|
98f9dbd734
feat: Triton Kernels for Punica (#613)
|
6 ヶ月 前 |
__init__.py
|
2bd6c92f73
fix: lora inclusion in wheels
|
1 年間 前 |
fully_sharded_layers.py
|
98f9dbd734
feat: Triton Kernels for Punica (#613)
|
6 ヶ月 前 |
layers.py
|
4d4e767838
ci: take one of fixing lint issues
|
6 ヶ月 前 |
lora.py
|
56e0b8223c
chore: add base class for LoRA-supported models
|
7 ヶ月 前 |
models.py
|
2a349ca3e1
fix: specify device when loading lora and embedding tensors
|
6 ヶ月 前 |
punica.py
|
98f9dbd734
feat: Triton Kernels for Punica (#613)
|
6 ヶ月 前 |
request.py
|
f92b9fc820
feat: support loading lora adapters directly from HF
|
6 ヶ月 前 |
utils.py
|
98f9dbd734
feat: Triton Kernels for Punica (#613)
|
6 ヶ月 前 |
worker_manager.py
|
f92b9fc820
feat: support loading lora adapters directly from HF
|
6 ヶ月 前 |