Show HN: Narwhal – LLM serving that moves GPUs between prefill/decode in seconds

2026-10-09来源 Hacker News ShowEnglish

Article URL: https://github.com/athrael-soju/Narwhal

Comments URL: https://news.ycombinator.com/item?id=50019698

Points: 1

# Comments: 0

原文：https://www.a8q9.cn/en/article/show-hn-narwhal-llm-serving-that-moves-gpus-between-prefill-decode-in-seconds-fa16cf.html

相关文章