ModelsSelected10月22日 17:26

vLLM Ships Day-0 Support for Sage-A1.5

官方账号vLLM@vllm_project

Post

Why we picked it

Day-0 support means the model can be self-hosted on existing vLLM infrastructure immediately, without waiting for community integrations. With only 3B active parameters, it targets teams running agentic workloads on modest local hardware who want an alternative to larger dense models. Developers comparing open-source MoE options for on-premise serving should evaluate its throughput against Qwen and DeepSeek MoE checkpoints.

vLLM announced day-0 support for Sage-A1.5, a 35B-parameter MoE model with 3B active parameters from Shanghai AI Lab. Users can deploy it locally with the command "vllm serve InternScience/Sage-A1.5". The model is positioned for agentic intelligence workloads that can be self-hosted from launch day.

Original · vLLM

🚀 Day-0 vLLM support for Sage-A1.5 (35B MoE, 3B active) from Shanghai AI Lab — agentic intelligence you can serve locally today:

vllm serve InternScience/Sage-A1.5

Congrats @sageai_official ! 🔥

#Sage-A1.5 #vLLM #Shanghai AI Lab #open-source models #agents

Keep reading

Recent stories with the same tag or section

Papers Builders10:10

Chinese contentSage-A1.5 发布：35B MoE 智能体模型强化长程任务与科学探索能力

一个 35B 的 MoE 智能体模型 Sage-A1.5，能让多个子智能体并行分工干活，还会自己检查进度、换思路，甚至做探索性科学研究。

#Sage-A1.5 #MoE #智能体 #开源模型

arXiv cs.AI@Wenjie Lou et al. (99)Source

Models Builders17:23

Chinese content米哈游联合清华、北大等高校开源 GameScaling 游戏模型，覆盖 0.8B 至 27B

米哈游和清华北大把游戏操作模型开源了，能自己玩《我的世界》和《毁灭战士》，最小 0.8B 单卡就能跑，可以拿来折腾。

#GameScaling #米哈游 #Qwen3.5 #开源模型

IT之家Source

Models BuildersSelected17:09

Tencent Hunyuan releases WorkForge agent training framework

Training agents on verifiable, evidence-grounded tasks addresses the core bottleneck of RL for long-horizon work: reward reliability. The 16.7K-environment scale makes this one of the larger open efforts in agent environment construction. Engineers building work or office agents can study the dual-verifier design for their own training pipelines.

#Tencent Hunyuan #WorkForge #agents #AI agents

官方账号腾讯混元@TencentHunyuanSource

Models Builders16:38

Chinese content中电信星辰实验室开源意图理解模型 Xing4.0-29B-Intent

中电信星辰实验室开源了 29B 的意图理解专用模型 Xing4.0-29B-Intent，做对话系统和意图识别的可以拿来试试。

#Xing4.0-29B-Intent #星辰 #中电信 #开源模型

量子位@量子位的朋友们Source

Models BuildersMulti-sourceSelected16:36

Muse Glimmer 30B: Meta's distilled agent model runs on one consumer GPU

Distilling from a large teacher into a small model specialised for long tool-use chains may matter more than raw size for local agents, a trade-off the OSWorld gap makes visible. Builders running agents on local hardware can use it as a drop-in for multi-tool MCP workflows without cloud dependency. Compared with Qwen3.6-27B, it wins on tool orchestration but loses on general OS-level tasks.

#Muse Glimmer #Meta #open-source models #agents

Event