vLLM and SGLang add Day-0 support for Ant Ling's open-source Ling-3.1-flash model
Article timeline
The articles in this story. Times are ET.
SGLang@sgl_projectOfficialSGLang adds Day-0 support for Ling-3.1-flash, a 560B MoE modelAISGLang announces Day-0 support for Ling-3.1-flash from AntLingAGI, a 560B-parameter MoE hybrid reasoning model with 25B active parameters and 1M context. MXFP4 and block-FP8 quantization reduce the weights from about 534GB to about 292GB, which the post says fits on 4 Hopper GPUs. The post also cites strong results on GDPVal-AA, FrontierSWE, and Terminal-Bench 4.0 for agent, office, and coding tasks.
vLLM@vllm_projectOfficialvLLM adds Day-0 support for Ling-3.1-flash, a 560B open-source modelAIvLLM announces Day-0 support for Ling-3.1-flash, which has about 560B total parameters, about 25B active per token, and up to 1M context. The model turns a rough brief into web pages, mobile UIs, and interactive prototypes, and users can serve it on their own infrastructure with vLLM. Ant Ling (@AntLingAGI) released the model as open source.
Ant Ling@AntLingAGIOfficialThanks to @sgl_project and @vllm_project for supporting the Ling family across open inference stacks. Their work gives developers more wa...AIThanks to @sgl_project and @vllm_project for supporting the Ling family across open inference stacks. Their work gives developers more ways to deploy and tune Ling models in their own infrastructure.