Vllm

DeepSeek open-sources DeepInfer, the inference framework behind V4.1-Flash: Deepseek is open-sourcing DeepInfer, the inference framework behind its V4.1-Flash model. The vLLM-based system cuts compute costs and energy use when running AI models. The release adds pricing pressure on Western providers including OpenAI and Anthropic.

AI Infrastructure • The Decoder

Axera launches AX8860 Edge AI chip series with 256 TOPS, up to 128 GB memory: Axera launched the AX8860 Edge AI chip series at CIIF 2026. The 6nm chips provide 256 TOPS and support up to 128 GB memory, with AXLink cascading and PCIe 5.0. The toolchain is vLLM/SGLang-friendly for on-site large-model inference.

Semiconductors • Pandaily