LLM Serving GPU Infrastructure Inference Optimization

Zyphra Inference

Serverless inference for frontier open-weight models

Serverless inference service launched with Zyphra Cloud for frontier open-weight language models, optimized for high-throughput, low-latency deployment on heterogeneous accelerator infrastructure.

Recent stories

1 linked story

releasePRIMARY2026-05-04

Zyphra Inference launches MI355X endpoints for DeepSeek V3.2, Kimi K2.6, and GLM 5.1

Zyphra launched serverless inference on AMD MI355X for DeepSeek V3.2, Kimi K2.6, and GLM 5.1, aimed at long-horizon agent workloads. The service leans on high-HBM nodes to keep more long-context sessions resident and reduce queueing.