Skip to content

Llm Inference

Topic archive • 3 matches

Back to home • GEO summary endpoint

2026-10-16

Technology

  • 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

    Permalink

2026-10-15

Technology

  • Study finds LLM reasoning uses 3.7× more inference energy on average: A study measured inference energy for 86 open-weight LLM checkpoints across seven benchmarks and six hardware platforms. Most configurations used a median 2.6–4.8× more energy than another configuration scoring at least as well, with gaps up to 27×; reasoning raised energy about 3.7× on average.

    AI Research • arXiv

    Permalink

2026-10-02

Tips

  • LLM Inference

    AIPerf tool benchmarks LLM inference performance at scale

    Permalink