gemini-4POST
Gemini 4 Argon 优化 vLLM，Gemma4 E2B 提速近 3 倍
开发者用 Gemini 4 Argon 改写 vLLM 代码，Gemma4 E2B 在 A100 上吞吐提升近 3 倍、最高多 108k t/s，且不损 token 一致性与质量。
Swarogan
@swarogan14 小时前收录原推发布于 2026.10.28
Swarogan @swarogan原推发布于 2026.10.28
Gemini 4 Argon finally came in handy for something. It improved the vllm code, speeding up Gemma4 E2B performance by almost 3x, without losing token consistency or quality. On A100, it's a jump of up to 108k t/s And I'm still waiting for Gemma5 https://x.com/googlegemma/status/2114757896563253305
这条是引用着另一条写的：「Gemini 4 Argon 让 Gemma 推理提速 2.85 倍」
x.com/swarogan/status/2115387092775870961采集于 2026.10.29 10:09