How we built the new fastest API for GLM-5.2
Alex Korte, Magdy Saleh, Tri Dao, Anant Desai, Bryce Dubayah, Abu Qader, Philip Kiely
Please rotate your device
To continue exploring this website, please rotate your device to a vertical orientation
Author
Tri Dao
- Model performanceAlex Korte, Magdy Saleh, Tri Dao, Anant Desai, Bryce Dubayah, Abu Qader, Philip Kiely
- Model performance
How we built the world’s fastest API for GLM-5.2
Alex Korte, Magdy Saleh, Tri Dao, Anant Desai, Bryce Dubayah, Abu Qader, Philip Kiely - Model performance
How we built the fastest GLM 5 API
Tri Dao, Philip Kiely, Madison Kanna - Research
How we built the fastest GLM-5 on Artificial Analysis
Madison Kanna, Tri Dao, Philip Kiely - Model performance
How we built the fastest Kimi K2.5 on Artificial Analysis
Tri Dao, Michael Feil, Abu Qader, Philip Kiely - Model performance
Kimi K2 Thinking at 140+ TPS on NVIDIA Blackwell
Abu Qader, Tri Dao, Philip Kiely - Model performance
How we made the fastest GPT-OSS on NVIDIA GPUs 60% faster
Tri Dao, Abu Qader, Philip Kiely - Model performance
How we run GPT OSS 120B at 500+ tokens per second on NVIDIA GPUs
Amir Haghighat, Tri Dao, Abu Qader, Bryce Dubayah, Philip Kiely