Joined May 2026
- Tweets 13
- Following 2
- Followers 622
- Likes 2
Photos and videos
Pinned Tweet
Jun 8
Proud to core-build this with the MiMo team! Breaking 1,000 TPS on a 1T model with standard 8-GPU nodes is just the beginning of the Speed Scaling era. Technical deep dive coming on our channel! 🚀⚡️
Jun 8
🚀 1,000 TOKENS/S ON A 1T MODEL! 🚀
We are thrilled to release Xiaomi MiMo-V2.5-Pro-UltraSpeed in collaboration with @TileRT_AI , breaking the 1,000 tokens/s output speed on a 1 Trillion parameter model for the FIRST TIME!
Not wafer-scale integration like Cerebras. Not pure on-chip SRAM chips like Groq. We achieve 1,000 tps on a 1T MoE model using just a SINGLE, STANDARD 8-GPGPU NODE.
Read the full technical deep dive：mimo.xiaomi.com/blog/mimo-ti…
Want to experience the future of real-time AI?
👉 Apply for UltraSpeed now: platform.xiaomimimo.com/ultr…
⏳ Limited-Time Access: Application-based · Jun 8 – Jun 23 (PDT)
💬 Chat Experience: Completely FREE for a limited time — try the blazing-fast web chat now.
⚡ UltraSpeed API: Just 3x the price for a ~10x boost in output experience.
🤝 Enterprise & Large-Scale Needs: business-mimo@xiaomi.com
7
8
38
5,691
Jun 8
How did we push a 1 Trillion parameter MoE model past the 1,000 TPS barrier on a standard 8-GPGPU node with @XiaomiMiMo? 🚀
It’s not just a faster kernel. It’s a total execution model revolution.
Key technical breakthroughs inside TileRT:
Jun 8
🚀 1,000 TOKENS/S ON A 1T MODEL! 🚀
We are thrilled to release Xiaomi MiMo-V2.5-Pro-UltraSpeed in collaboration with @TileRT_AI , breaking the 1,000 tokens/s output speed on a 1 Trillion parameter model for the FIRST TIME!
Not wafer-scale integration like Cerebras. Not pure on-chip SRAM chips like Groq. We achieve 1,000 tps on a 1T MoE model using just a SINGLE, STANDARD 8-GPGPU NODE.
Read the full technical deep dive：mimo.xiaomi.com/blog/mimo-ti…
Want to experience the future of real-time AI?
👉 Apply for UltraSpeed now: platform.xiaomimimo.com/ultr…
⏳ Limited-Time Access: Application-based · Jun 8 – Jun 23 (PDT)
💬 Chat Experience: Completely FREE for a limited time — try the blazing-fast web chat now.
⚡ UltraSpeed API: Just 3x the price for a ~10x boost in output experience.
🤝 Enterprise & Large-Scale Needs: business-mimo@xiaomi.com
8
7
58
9,973
Jun 8
The era of Speed Scaling has arrived. Read our full technical deep dive into the microsecond-scale execution reality & Co-design specs here: tilert.ai/blog/breaking-1000…
📦 GitHub: github.com/tile-ai/TileRT
5
14
1,427
Jun 8
⚡️ System & Model Co-design: Deep technical synergy with the MiMo team on FP4/FP8 mixed quantization and production-grade DFlash.
5
1,163
Jun 8
⚡️ Heterogeneous Workers & Warp Specialization: Breaking the serial pace to orchestrate specialized worker groups not just within a single SM, but scaling across the entire GPU execution domain.
5
1,076
Jun 8
⚡️ Tile-grained Pipelining: Deeply overlapping memory movement, tensor computation, and communication at the physical tile level.
4
967
Jun 8
⚡️ Persistent Kernels: The entire compute pipeline runs continuously inside the GPU, enabling full-stack continuous prefetching and erasing operator boundaries.
5
753
May 24
感谢鸭哥的博客推荐，我们还会有新的惊喜，欢迎继续关注❤️
智谱 GLM-5.1 高速版 API 达到 400 tokens/s。这不是优化得更快，而是从执行模型层面重构了 GPU 推理。深度分析了 TileRT 的技术原理，以及推理速度为什么正在成为 AI API 的第二条竞争轴。 yage.ai/share/glm51-highspee…
1
2
677
May 22
TileRT❤️Z.ai 🚀🚀🚀
GLM-5.1-highspeed is coming, 400 tokens per second. Very expensive, but bring a new possibility.
3
617
