Compiler optimizations for 5.8ms GPT-OSS-120B inference (not on GPUs) Posted by olibaw on Friday October 17, 2025 @02:51PM from the furiosa.ai dept. https://furiosa.ai/blog/serving-gpt-oss-120b-at-5-8-ms-tpot-with-two-rngd-cards-compiler-optimizations-in-practice ( no comments | on HN )
There are no comments yet.