| .. |
|
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 8 meses |
|
abstract.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
blocksparse_attn.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
flash_attn.py
|
24456206a9
fix: logit softcapping in flash-attn (#688)
|
hai 4 meses |
|
flashinfer.py
|
300f889554
chore: update flashinfer to v0.1.3 (#685)
|
hai 4 meses |
|
ipex_attn.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
openvino.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
pallas.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
placeholder_attn.py
|
bf88c8567e
feat: mamba model support (#674)
|
hai 4 meses |
|
rocm_flash_attn.py
|
e200775863
feat: enable using fp8 kv and prefix caching with chunked prefill (#668)
|
hai 4 meses |
|
torch_sdpa.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
utils.py
|
3bbb3f2086
feat: add numpy implementation of `compute_slot_mapping` (#678)
|
hai 4 meses |
|
xformers.py
|
e200775863
feat: enable using fp8 kv and prefix caching with chunked prefill (#668)
|
hai 4 meses |
AlpinDale
24456206a9
fix: logit softcapping in flash-attn (#688)