Standard Kernel says AI-written software made abandoned Intel Gaudi beat NVIDIA's H100
anneouyang · x · 2026-11-19
Standard Kernel claims it made Intel's abandoned Gaudi chips outperform NVIDIA's H100 for inference by using AI to write the software stack — arguing hardware alone doesn't determine performance or economics. Veteran hardware engineer Julie Choi, who amplified the post, says the future of AI compute is heterogeneous and unlocking max performance across NVIDIA, AMD, Intel, Qualcomm, Arm and Cerebras always requires rethinking the software stack, and is watching what the team does next with production GPUs and wafer-scale engines.
Related event: AI-Written Software Stack Makes Abandoned Intel Gaudi Outperform H100(2 posts)→
More from Infra
- KAIST Proposes PROLA: Low-Rank Adaptation for Spatiotemporal Weather Downscaling — MLVLab · 2026-11-19
- MIT's QDA uses LLM agents to auto-design quantization, beating best public recipes — mit-han-lab · 2026-11-19
- WSJ: Wall Street pledged $500B for Nvidia but hasn't put up a dime — GaryMarcus · 2026-11-19
- Bypassing PyTorch with HIP kernels makes MiniMax H3 up to 3x faster on AMD R9700 — Apprehensive_Sky892 · 2026-11-19
- Ex-DeepSeek core member open-sources Linger, a local AI agent claiming 5x faster inference — Aiden_Tech_Ai · 2026-11-19
- China opens first overseas-targeted AI cluster on Huawei Ascend chips — pstAsiatech · 2026-11-19