 AlpinDale
|
d34e083c48
feat: add experts_int8 support (#730)
|
vor 4 Monaten |
|
AlpinDale
|
4ec08af18b
chore: update fused MoE weight loading (#700)
|
vor 4 Monaten |
|
AlpinDale
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
vor 4 Monaten |
|
AlpinDale
|
3f712cd287
feat: add progress bar for loading individual weight modules (#640)
|
vor 4 Monaten |
|
AlpinDale
|
bf88c8567e
feat: mamba model support (#674)
|
vor 4 Monaten |
|
AlpinDale
|
8583aefed7
chore: mamba cache single buffer (#673)
|
vor 4 Monaten |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
