HN Radio.daily Hacker News, read aloud

← all entities

vLLM

product · 1 story across the archive · newest first · hardware

0 mentions in Jul 20250 mentions in Aug 20250 mentions in Sep 20250 mentions in Oct 20250 mentions in Nov 20250 mentions in Dec 20250 mentions in Jan 20260 mentions in Feb 20260 mentions in Mar 20260 mentions in Apr 20260 mentions in May 20262 mentions in Jun 2026mentions by month
mixed HN liked the technical depth and saw the guide as a meaningful step toward practical homelab-scale local AI, especially for unified-memory Strix Halo systems. But the thread was dominated by cost, availability, and performance caveats: Strix Halo pricing has jumped sharply, PCIe x4 limits the 100GbE cards to roughly 50 — latest discussion,
often appears withROCmAMD Strix HaloRayRCCLRoCE v2
  1. A two-node Strix Halo RDMA recipe for local LLM inference▲ 231 · 87 commentsin 2 episodes: · 11:30 · 3:15