| .. |
|
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
há 8 meses atrás |
|
abstract.py
|
4d4e767838
ci: take one of fixing lint issues
|
há 4 meses atrás |
|
blocksparse_attn.py
|
614ca6b0bf
feat: support logits soft capping with flash attention backend
|
há 4 meses atrás |
|
flash_attn.py
|
6c1eab6a6c
feat: non-blocking transfer in prepare_input
|
há 4 meses atrás |
|
flashinfer.py
|
6c1eab6a6c
feat: non-blocking transfer in prepare_input
|
há 4 meses atrás |
|
ipex_attn.py
|
614ca6b0bf
feat: support logits soft capping with flash attention backend
|
há 4 meses atrás |
|
openvino.py
|
0886c361f4
feat: OpenVINO CPU backend (#576)
|
há 5 meses atrás |
|
pallas.py
|
614ca6b0bf
feat: support logits soft capping with flash attention backend
|
há 4 meses atrás |
|
rocm_flash_attn.py
|
4d4e767838
ci: take one of fixing lint issues
|
há 4 meses atrás |
|
torch_sdpa.py
|
614ca6b0bf
feat: support logits soft capping with flash attention backend
|
há 4 meses atrás |
|
utils.py
|
0e6c400b13
feat: re-add GGUF (#600)
|
há 4 meses atrás |
|
xformers.py
|
614ca6b0bf
feat: support logits soft capping with flash attention backend
|
há 4 meses atrás |
AlpinDale
4d4e767838
ci: take one of fixing lint issues