.. |
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hace 8 meses |
abstract.py
|
1390915778
multi-step: add support for flashinfer attention backend (#1033)
|
hace 2 semanas |
blocksparse_attn.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hace 1 mes |
flash_attn.py
|
1390915778
multi-step: add support for flashinfer attention backend (#1033)
|
hace 2 semanas |
flashinfer.py
|
1390915778
multi-step: add support for flashinfer attention backend (#1033)
|
hace 2 semanas |
ipex_attn.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hace 1 mes |
openvino.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hace 1 mes |
pallas.py
|
032974a28a
tpu: fix TPU type api (#975)
|
hace 2 semanas |
placeholder_attn.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
hace 2 semanas |
rocm_flash_attn.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hace 3 semanas |
torch_sdpa.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hace 1 mes |
utils.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
hace 2 semanas |
xformers.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hace 1 mes |