Google· @Google · X·· 2 小时前AI 评分51
AI 导读
Google 介绍 Gemini 4 Argon 对开源模型 Gemma 的优化：仅用几天就把 Gemma 4 E2B 在 A100 上经 vLLM 实现约 2.85x 推理加速，从约 37,900 提升到超过 108,000 tokens 每秒，且保持 100% token 一致、零质量下降。视频演示了同时生成 64 个实时 Python 模拟。
正文
Gemini 4 Argon is also speeding up our @GoogleGemma open models — making them nearly three times as fast.
In just a few days, Argon optimized Gemma 4 E2B to achieve a 2.85x inference speedup on an A100 via vLLM, jumping from ~37,900 to over 108,000 tokens per second with 100% token parity and zero quality drop.
Here’s that speedup in action, generating 64 live Python simulations at once ↓
https://x.com/osanseviero/status/2110096066293207535/video/1
来源：Google · x.com