LLM inference

Discover insights, guides, and tutorials tagged with “LLM inference.”

2 Articles

OpenTPU: An Open-Source AI Accelerator, Developed by AI

OpenTPU: An Open-Source AI Accelerator, Developed by AI

openTPU is a small, readable LLM decode accelerator with its entire stack in one repo: RTL, ISA, simulator, compiler and profiler. See how A...

#open-source hardware #LLM inference #AI agents

Arpan Singh

Oct 7, 2026

8 min

Qwen3.8-27B Hits Cerebras at 1,500 Tokens a Second: The Full Picture

Qwen3.8-27B Hits Cerebras at 1,500 Tokens a Second: The Full Picture

Qwen3.8-27B is live on Cerebras at ~1,500 tokens/sec, confirmed on its dedicated model page rather than the general catalog the HN post link...

#Cerebras #LLM inference #Qwen3.8-27B

Pushpum Vats

Sep 4, 2026

6 min