作者 | SHA1 备注 | 提交日期 |
---|---|---|
|
d638dc592d fix: some minor typing issues in spec decode | 5 月之前 |
|
16dff9babc chore: enable bonus token in spec decoding for KV cache based models | 5 月之前 |
|
abbb730607 feat: support draft model on different tensor parallel size | 6 月之前 |
|
ec5b99d075 fix: use named args | 6 月之前 |
|
e0886ee929 feat: add `ProposerWorkerBase` abstract class | 6 月之前 |