HN Radio.daily Hacker News, read aloud

← all entities

ROCm

technology · 2 stories across the archive · newest first · ai

0 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 20261 mention in Jun 20265 mentions in Jul 2026mentions by month
mixed Commenters were interested in AMD as a real alternative to scarce and expensive Nvidia capacity, but the thread was notably skeptical of the framing. The biggest objections were that performance-per-dollar is incomplete without power, cooling, and datacenter constraints, and that FP4 quantization may reduce model quali — latest discussion,
often appears withGLM-5.2AMDNVIDIAAMD Strix HaloRayRCCL
  1. AMD inference gets cheaper per token, but HN wants the watt bill▲ 358 · 136 commentsin 5 episodes: · 1:33 · 1:34 · 1:32 · 2:45 · 1:40
  2. Strix Halo gets a two-node RDMA playbook for local vLLM▲ 231 · 87 comments · 3:15