AlpinDale
|
e0886ee929
feat: add `ProposerWorkerBase` abstract class
|
vor 7 Monaten |
AlpinDale
|
a94de94c44
refactor: combine the prefill and decode into a single API (#553)
|
vor 7 Monaten |
AlpinDale
|
16f345c29a
fix circular reference with weakref
|
vor 7 Monaten |
AlpinDale
|
ef733aee43
implement ExecuteModelData to reduce executor complexity
|
vor 8 Monaten |
AlpinDale
|
723c6acb84
re-add ngram speculative decoding
|
vor 8 Monaten |
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
vor 10 Monaten |
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
vor 11 Monaten |