Disaggregated Inference at Scale with PyTorch and VLLM (pytorch.org)

2 points by djhu9 1y ago ↗ HN

0 comments

[ 15.2 ms ] story [ 91.8 ms ] thread

No comments yet.

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

Source · Live DB stats