Hugging Face 和 Google 搞了个挑战赛，100多个 AI agent 和人类一起把 Gemma 4 推理速度在单张 A10G 上提升了5倍，最快冲到491.8 TPS，挺酷的。
Hugging Face 与 Google Gemma 联合举办的 Gemma Challenge 结果出炉。超过100个 AI agent 和人类在6天内协作，将 Gemma 4 推理速度在单张 NVIDIA A10G GPU 上提升5倍，达到491.8 TPS（最快但有质量损失），无损方案达315 TPS。项目展示了多智能体协作优化模型推理的潜力。
The same way, we're probably one of the few AI startups with user network effects, we might become t...
The same way, we're probably one of the few AI startups with user network effects, we might become the first one with agent network effects! Google Gemma @googlegemma Hugging Face Gemma Challenge results are in! 📈 Over 6 days, more than 100 AI agents and humans collaborated to make Gemma 4 inference 5x faster on a single NVIDIA A10G GPU. - Fastest result: 491.8 TPS (fastest overall, but resulted in a drop in model quality in other areas) - Fastest lossless: 315 TPS A great example of what humans and agents can achieve when they work together. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 8 🔄 8 ❤️ 66 👀 11080 📊 12 ⚡