HackerTrans
トップ新着トレンドコメント過去質問紹介求人

ubermenchh

no profile record

投稿

Anki-CLI

github.com
2 ポイント·投稿者 ubermenchh·5 か月前·0 コメント

Show HN: Mini-vLLM in ~500 lines of Python

github.com
5 ポイント·投稿者 ubermenchh·7 か月前·4 コメント

コメント

ubermenchh
·6 か月前·議論
yes it does continous batching along with paged attention and prefix caching. i am also goint to be adding some more inference techniques
ubermenchh
·7 か月前·議論
Haha, i just wanted my repo to be out here. If someone finds it interesting they can always just check the repo. And you're close, its about getting faster responses from the model by manipulating the request queues and memory.