Menu

#Container

253 posts

Feed·
20 of 253 posts
GitHub - sqliteai/waste: Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
📰
0

GitHub - sqliteai/waste: Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

Hacker News·Hacker News·about 2 months ago
#i9E3YRcs
#github#container#waste#cache#token#engine

Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine. - sqliteai/waste

15s
Read More