ParthSareen
|
f257f1fd04
sample: do all sorting in topK
|
hai 1 mes |
ParthSareen
|
8b1ae03302
sample: simplify top_k=0 sorting
|
hai 1 mes |
ParthSareen
|
db10a7da88
sample: use container/heap for top_k
|
hai 1 mes |
Parth Sareen
|
7e34f4fbfa
sample: add numerical stability to temperature/softmax transform (#9631)
|
hai 1 mes |
Jeffrey Morgan
|
e093db92c4
sample: temporarily use grammars for constrained generation in new engine (#9586)
|
hai 1 mes |
Parth Sareen
|
0682dae027
sample: improve ollama engine sampler performance (#9374)
|
hai 2 meses |
Parth Sareen
|
0b7e1676eb
sample: add sampling package for new engine (#8410)
|
hai 2 meses |