| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
hai 1 ano |
|
block.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
hai 4 meses |
|
config.py
|
5d37ec1016
suppress tpu import warning (#696)
|
hai 4 meses |
|
connections.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
grammar.py
|
0527131e93
fix: grammar logits processor (#268)
|
hai 11 meses |
|
logger.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
logits_processor.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 8 meses |
|
outputs.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
hai 4 meses |
|
pooling_params.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
|
sampling_params.py
|
2da6a3ec2b
feat: option to apply temperature scaling last (#670)
|
hai 4 meses |
|
sequence.py
|
ef40c05cd3
fix: minor adjustments to scheduler and block manager (#667)
|
hai 4 meses |
|
test_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 8 meses |
|
utils.py
|
5d37ec1016
suppress tpu import warning (#696)
|
hai 4 meses |
AlpinDale
5d37ec1016
suppress tpu import warning (#696)