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.
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15