AI Trends

Trending story

English translation is being prepared.

1 reports1 story updatesUpdated Nov 18 08:00

Understand this story

Story summary

The English summary is being updated. See the reporting timeline below.

Latest development · Report

SGLang Integrates Humming 0.1.18, Expanding Support for Low-Bit MoE Inference

Developments

1 confirmed developments

  1. English translation is being prepared.

    Source:LMSYS Blog

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 18

  1. LMSYS BlogFirst-party

    SGLang Integrates Humming 0.1.18, Expanding Support for Low-Bit MoE Inference

    SGLang has integrated Humming 0.1.18, bringing more quantization schemes and GPU architectures to its low-bit dense and MoE inference kernels while retaining the framework’s routing, scheduling, and distributed execution capabilities. When running DeepSeek-V4.1-Flash-1017 on eight H20-3e GPUs, Humming delivers a 1.07–1.23× prefill speedup over Marlin at the same A16 precision; after Humming EP1 switches to AFP8, decoding throughput increases by 16.79–34.41%. The article also explains the compute paths for Hopper and Blackwell, SGLang configuration, and related quality evaluation results.

Related stories

  1. Related storiesQwen Releases Qwen4-Max Preview Version
  2. Related storiesMiniMax releases the H3-Image image model and opens the weights
  3. Related storiesBaidu Wenxin releases ERNIE 5.5 Flash Preview
  4. Related storiesMistral releases Large 4 weights on Hugging Face