LLM Inference with Ray: Expert parallelism and prefill/decode disaggregation (anyscale.com)

1 points by mycelia 7mo ago ↗ HN

0 comments

[ 2.6 ms ] story [ 14.1 ms ] thread

No comments yet.

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

Source · Live DB stats