LMSYS Org
🎬 Ollama Gemma Day Recap: SGLang at the Ollama Gemma 4 Party in Palo Alto 🍾 Last night, @ollama hosted a packed Gemma Day at the Palo Alto office alongside the @GoogleDeepMind Gemma team. SGLang was invited to do a very cool demo to close out the night. 🧠 The… https://twitter.com/lmsysorg/status/2044888006730072171/photo/1
中文: 🎬 奥拉玛·杰玛日回顾:在帕洛阿尔托举行的奥拉玛·杰玛4派对上 🍾 昨晚，@ollama 与 @GoogleDeepMind Gemma 团队一起在帕洛阿尔托办公室举办了一场拥挤的杰玛日活动。斯格朗受邀进行一场非常酷的演示，以结束当晚的活动。 🧠 网址:
2026-04-16 21:17:47
LMSYS Org
Excited to be part of @ollama Gemma Day tomorrow in Palo Alto! Khoa Pham (@kwafam7) from @radixark will demo Gemma 4 in production with SGLang 🚀 Come say hi! 📷 RSVP: https://luma.com/ollama-gemma4
中文: 很高兴明天能参加在帕洛阿尔托举行的@ollama Gemma Day!来自@radixark的Khoa Pham(@kwafam7)将与SGLang 🚀一起演示《Gemma 4》的制作 快点说吧! 📷 RSVP:
2026-04-14 19:42:18
LMSYS Org
🎉 Congrats on releasing MiniMax M2.7 from @MiniMax_AI, the first model deeply participating in its own evolution. Day-0 support is now live in SGLang! 🤖 Model self-evolution: autonomously optimized a scaffold over 100+ rounds with 30% performance gain 🏆 MLE Bench Lite: 66.6%… https://twitter.com/lmsysorg/status/2043132465783689715/photo/1
中文: 🎉 恭喜从 @MiniMax_AI 发布了 MiniMax M2.7，这是首款深度参与自身演进的机型。SGLang 现已上线，支持 Day-0 现已上线! 🤖 模型自进化:自主优化了100多发的支架，性能提高30% 🏆 MLE Bench Lite:66.6%...
2026-04-12 01:01:54
LMSYS Org
🎉 Congrats to @Zai_org on releasing GLM-5.1, SGLang is ready to support on day-0! GLM-5.1 is a next-gen flagship built for agentic engineering: 🏆 SWE-Bench Pro: #1 open source, #3 globally 🔨 Terminal-Bench 2.0: top-ranked on real-world terminal tasks ⏳ Long-Horizon: runs… https://twitter.com/lmsysorg/status/2041553264685334588/photo/1
中文: 🎉 祝贺@Zai_org 发布 GLM-5.1，SGLang 已准备好在第 0 天提供支持! GLM-5.1 是为代理工程打造的下一代旗舰产品: 🏆 SWE-Bench Pro:全球第一开源，第3名 🔨 终端台2.0:在实际终端任务中排名第一 ⏳ 长至地平线:运行...
2026-04-07 16:26:43