 AlpinDale
|
8d77c69cbd
feat: support image processor and add llava example
|
vor 7 Monaten |
|
AlpinDale
|
e4ea3da1ad
fix: tensor parallel with embedding model
|
vor 7 Monaten |
|
AlpinDale
|
de62ceb18c
refactor: eliminate parallel worker per-step task scheduling overhead
|
vor 8 Monaten |
 AlpinDale
|
a94de94c44
refactor: combine the prefill and decode into a single API (#553)
|
vor 8 Monaten |
|
AlpinDale
|
50b7c13db0
refactor: attention selector (#552)
|
vor 8 Monaten |
|
AlpinDale
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
vor 8 Monaten |
