MLX-Serve v26.9.1 Ships: One-Shot Qwen Flash Runs from a Single Screenshot
TheMoonMidas · x · 2026-09-04
MLX-Serve v26.9.1 is out, built by @pidotdev with heavy optimization and correctness testing from @Beamsters1. The author demos pasting a screenshot containing a prompt and getting a one-shot correct output running Alibaba's Qwen Flash, calling the model "truly amazing."
More from Infra
- Nvidia guides 70% growth citing unmet AI demand, while media panics over a $500M Korean neocloud IPO — firstadopter · 2026-10-21
- Pichai: everyone is massively short on AI compute — 'everyone wishes you had two times what you had planned' — firstadopter · 2026-10-21
- Stanford CS336 Lecture 6: fused Triton kernels cut softmax memory traffic ~4x — stanfordnlp · 2026-10-21
- General Compute partners with Positron AI: Atlas memory-centric hardware ships Q1 2027 — aftahi_ai · 2026-10-21
- AI bond issuance hits $419B in 2026, up 90% from all of 2025 — SumitGup · 2026-10-21
- AI Obsession Is Making Enterprises Neglect Cloud FinOps, Expert Warns — DavidLinthicum · 2026-10-21