| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
il y a 1 an |
|
block.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
il y a 5 mois |
|
config.py
|
7222b84582
feat: ministral support (#776)
|
il y a 3 mois |
|
connections.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 5 mois |
|
grammar.py
|
8a71788372
Add OLMoE (#772)
|
il y a 3 mois |
|
logger.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 5 mois |
|
logits_processor.py
|
8a71788372
Add OLMoE (#772)
|
il y a 3 mois |
|
outputs.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
il y a 5 mois |
|
pooling_params.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 5 mois |
|
sampling_params.py
|
ad181e3fef
feat: bring back dynatemp (#754)
|
il y a 4 mois |
|
sequence.py
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
il y a 5 mois |
|
test_utils.py
|
8a71788372
Add OLMoE (#772)
|
il y a 3 mois |
|
utils.py
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
il y a 5 mois |
AlpinDale
7222b84582
feat: ministral support (#776)