OpenAI Rewrites Inference Stack in Assembly, Trending Away from PyTorch

SumitGup · x · 2026-08-28

Citing SemiAnalysis' OpenAI Jalapeño blog, a post reveals OpenAI has rewritten its entire inference stack in pure assembly without frameworks, achieved via hillclimbing. Following xAI's move to C, the trend suggests frontier labs will converge on AI-generated C/assembly stacks. This marks the decline of traditional ML frameworks like PyTorch at the frontier, returning to low-level optimization for serving.

Original post →

More from Infra

Infra channel →