Zyphra ships second wave of MI355X inference optimizations for MoE and long-context
teortaxesTex · x · 2026-10-21
Zyphra announced a second wave of inference optimizations for AMD Instinct MI355X GPUs, powered by its Zyphra Optimization Engine (ZOE).
The engineering blog details the kernel-level work behind faster MoE and long-context serving for frontier open models, representing a notable engineering investment in the AMD inference stack.
More from Infra
- ByteDance, Alibaba, Tencent order 3M+ Nvidia RTX PRO 5500 cards worth $35B, Reuters reports — SumitGup · 2026-10-21
- TorchTPU demo: unified vLLM & SGLang backend for LLM serving on TPUs — Rob_Mulla · 2026-10-21
- Google, Red Hat release llm-d 1.0: open K8s-native distributed inference stack — rseroter · 2026-10-21
- acs infra launches free base model API offering Llama 3.1 8B and 405B for LLM psychology researchers — amplifiedamp · 2026-10-21
- Developer Moves AI Agents to a Dedicated Linux Workstation Using Incus System Containers — kevinkern · 2026-10-21
- Nvidia guides 70% growth citing unmet AI demand, while media panics over a $500M Korean neocloud IPO — firstadopter · 2026-10-21