| .. |
|
guided_decoding
|
0256ed236b
feat: windows support (#790)
|
il y a 2 mois |
|
layers
|
273c61d406
guard against nan temperature from dynatemp (or anywhere else).
|
il y a 1 mois |
|
model_loader
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
il y a 2 mois |
|
models
|
0256ed236b
feat: windows support (#790)
|
il y a 2 mois |
|
__init__.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
il y a 4 mois |
|
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
il y a 4 mois |
|
parameter.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
il y a 2 mois |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 4 mois |
|
sampling_metadata.py
|
ed87b5dd32
remove special-case values for prompt sequences
|
il y a 3 mois |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
il y a 8 mois |
50h100a
273c61d406
guard against nan temperature from dynatemp (or anywhere else).