Inception Labs launches Mercury 3, a diffusion LLM claiming 1000 tok/s inference
cmrdporcupine · hn · 2026-10-20
Inception Labs unveiled Mercury 3, a diffusion-based LLM that claims inference speeds of up to 1000 tokens per second, far above typical autoregressive models. By generating tokens in parallel instead of sequential decoding, diffusion LLMs are positioned as a low-latency alternative; the HN thread debates quality and practical trade-offs.
More from Infra
- Gartner: $3.5T of AI infra spend may face write-downs by 2030, 80% of neoclouds to fold — rohanpaul_ai · 2026-10-20
- Stripe paid $7.5B for a router, but routing is easy — verifying outputs is the real moat — AIGODSEND · 2026-10-20
- Google Cloud upgrades VPC Service Controls with folder-level perimeters for agent traffic, free — rseroter · 2026-10-20
- Amateur researcher fights Stage 4 colon cancer with ML, hits $500-per-run GPU wall — whafa · 2026-10-20
- Citi projects $5.35 trillion in cumulative capex from Amazon, Microsoft, Google and Meta through 2030 — Beth_Kindig · 2026-10-20
- DisaggKD paper splits teacher and student across nodes to lift KD memory limits — Ruixuan Tu · 2026-10-20