Codex doubles per-user throughput overnight
TheZachMueller · x · 2026-07-20
The author says Codex ended the night at 2× tok/s per user.
The quoted update adds the context:
- It was already running at 20 tok/s/user.
- The setup used 10GbE and a 4/2 split of GPUs between nodes.
- The gains came before optimization and with speculative decoding already in use.
In other words, this is a small but concrete performance update for a coding-agent system, with some infrastructure details behind the throughput improvement.
Related event: Codex Doubles Per-User Throughput(2 posts)→
More from coding & agent
- Devin Outposts aims to run AI agents on any machine, from Mac minis to Kubernetes clusters — blaizedsouza · 2026-07-22
- Devin adds e2b sandboxes for remote agent execution — badphilosopher · 2026-07-22
- Hermes Agent Refactoring Proposal: Decoupling via Event Bus and Monorepo Slicing — Promptmethus · 2026-07-22
- ty now reads Pydantic config keywords and field metadata — charliermarsh · 2026-07-22
- Pensar Launches AI Security Agent to Autonomously Discover and Patch 0-Days — andriy_mulyar · 2026-07-22
- ty adds first-class Pydantic support, including strict and lax field handling — charliermarsh · 2026-07-22