WHAT NEW IN X10.28 WED

X 上的 AI 合集档案 · 22 个合集 · 58,925 条

benchmarkVIDEO

Apple 发布 RSI-Inference Bench 推理工程基准

Apple ML Research 用真实 vLLM/SGLang 任务构建基准,测试 AI agent 能否优化推理系统,最佳 agent 仅 26.7% pass@1。

Ruixiang Zhang
@onloglogn11 天前收录原推发布于 2026.10.17
Ruixiang Zhang @onloglogn原推发布于 2026.10.17
在 X 上打开原推

Introducing RSI-Inference Bench from 🍎 Apple ML Research 🌐 http://rsi-inference.com 💻 https://github.com/apple-aiml-research/ml-rsi-inference-bench Can AI agents improve the systems that run AI? We spent $100K API tokens, 50K GPU hours to find out. We built environments and benchmark from real-world #vLLM and #SGLang tasks, covering the full lifecycle of model inference engineering: 🚀 Day-0 Model Support ⚡ Inference Optimization 🔧 Bug Fix → Unsaturated: best agent at 26.7% pass@1 → Comprehensive coverage of the inference stack → Verifiable rewards: binary and continuous Watch the video to find out more!

x.com/onloglogn/status/2111170954944823685采集于 2026.10.17 10:23