| .. |
|
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
9 달 전 |
|
abstract.py
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
1 개월 전 |
|
blocksparse_attn.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
2 달 전 |
|
flash_attn.py
|
7fffa507ff
build: build flash attention kernels inside aphrodite (#1085)
|
2 주 전 |
|
flashinfer.py
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
1 개월 전 |
|
ipex_attn.py
|
6951928522
xpu: bump IPEX to 2.3, support GQA (#1042)
|
1 개월 전 |
|
openvino.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
2 달 전 |
|
pallas.py
|
032974a28a
tpu: fix TPU type api (#975)
|
1 개월 전 |
|
placeholder_attn.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
1 개월 전 |
|
rocm_flash_attn.py
|
d9d287a288
rocm: enable multi-step scheduling for rocm (#1071)
|
1 개월 전 |
|
torch_sdpa.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
2 달 전 |
|
utils.py
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
1 개월 전 |
|
xformers.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
2 달 전 |
AlpinDale
7fffa507ff
build: build flash attention kernels inside aphrodite (#1085)