| .. |
|
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
há 10 meses atrás |
|
abstract.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 6 meses atrás |
|
blocksparse_attn.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 6 meses atrás |
|
flash_attn.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
há 6 meses atrás |
|
flashinfer.py
|
67ee885293
fix: flashinfer outputs (#657)
|
há 6 meses atrás |
|
ipex_attn.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 6 meses atrás |
|
openvino.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 6 meses atrás |
|
pallas.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 6 meses atrás |
|
placeholder_attn.py
|
bf88c8567e
feat: mamba model support (#674)
|
há 6 meses atrás |
|
rocm_flash_attn.py
|
e200775863
feat: enable using fp8 kv and prefix caching with chunked prefill (#668)
|
há 6 meses atrás |
|
torch_sdpa.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 6 meses atrás |
|
utils.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
há 6 meses atrás |
|
xformers.py
|
e200775863
feat: enable using fp8 kv and prefix caching with chunked prefill (#668)
|
há 6 meses atrás |
AlpinDale
bf88c8567e
feat: mamba model support (#674)