vLLM splits prefill and decode graph sizes, GLM MTP norm aligned
- [Perf] R3: Keep the routed-expert host cache only on the output rank (1/3) sgl-project/sglang
$ git log --author="byronhsu" --all --oneline
Every morning, RepoJournal's newsroom reads what shipped across the open-source projects developers depend on — and writes the wire. Your commits kept making the news. This is your clippings file: the stories where your work was the story.
1
story filed
1
daily wire
$ grep -rn "author: byronhsu" wires/ | sort -r