AlpinDale
|
d638dc592d
fix: some minor typing issues in spec decode
|
5 months ago |
AlpinDale
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
5 months ago |
AlpinDale
|
abbb730607
feat: support draft model on different tensor parallel size
|
5 months ago |
AlpinDale
|
ec5b99d075
fix: use named args
|
5 months ago |
AlpinDale
|
e0886ee929
feat: add `ProposerWorkerBase` abstract class
|
5 months ago |