zagwdt — HRO

Alpha This system is experimental. Scores and classifications are early-stage research and may be unreliable. Methodology →

zagwdt 89 karma 2y 5m on HN HN profile →

Coverage

We've seen 2 of ~6 submissions

Full eval: 0 Lite-only: 0 Unevaluated: 2

2 stories

1.		TorchSpec: Speculative Decoding Training at Scale (pytorch.org)
		2 points by zagwdt 1 days ago \| 0 comments \| skipped
2.		Flash Attention 4 (www.together.ai)
		1 points by zagwdt 18 days ago \| 0 comments \| skipped

build ee2b489+gzrb · deployed 2026-03-10 22:52 UTC · evaluated 2026-03-16 02:03:38 UTC