vLLM TorchTPU: Zero-copy KV cache offloading and disaggregated serving (vllm.ai)

1 points by mikemo88 6d ago ↗ HN

0 comments

[ 0.26 ms ] story [ 5.5 ms ] thread

No comments yet.

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

Source · Live DB stats