| .. |
|
guided_decoding
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesi fa |
|
layers
|
1394008421
chore: decouple `should_modify_greedy_probs_inplace (#671)
|
6 mesi fa |
|
model_loader
|
3f49a55f82
feat: add INT8 W8A16 quant for TPU (#663)
|
6 mesi fa |
|
models
|
bf88c8567e
feat: mamba model support (#674)
|
6 mesi fa |
|
__init__.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
6 mesi fa |
|
_custom_op.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesi fa |
|
parameter.py
|
f1e1d0bd3d
feat: introduce `BaseAphroditeParameter` (#646)
|
6 mesi fa |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesi fa |
|
sampling_metadata.py
|
2da6a3ec2b
feat: option to apply temperature scaling last (#670)
|
6 mesi fa |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 mesi fa |
AlpinDale
bf88c8567e
feat: mamba model support (#674)