데이터 이동 병목 해결을 통한 LLM 추론 전용 ASIC 'Jalapeño' 개발
OpenAI and Broadcom's Jalapeño, a Custom Inference ASIC: Inference ASIC vs GPU
OpenAI and Broadcom's Jalapeño, a Custom Inference ASIC: Inference ASIC vs GPU
AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm
Why Your PyTorch Training Crawls on a Beefy GPU (And How to Fix It)