ServerlessLLM: Low-Latency Serverless Inference for Large Language Models (arxiv.org)

2 points by geuds 1y ago ↗ HN

0 comments

[ 3.2 ms ] story [ 7.4 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats