AITOPAI热报
ModelsSelected73°

Hy4 preview runs in vLLM

Hunyuan@TXhunyuan
Post· 2 sources
View the post
Why we picked it

Tencent's Hy4-preview model integrates with vLLM, offering developers in ASEAN access to a large MoE model with efficient sparse attention.

Tencent's Hy4-preview model runs in vLLM from day 0, verified on NVIDIA GPUs. The model has 770B total parameters with 49B active and 256 routed experts plus one shared. It supports 1M context length but each query attends to just 2048 tokens. Only 21 of the 78 layers compute their own sparse index, while the other 57 reuse one.

Original · Hunyuan

Hy4 preview runs in vLLM vLLM @vllm_project @TencentHunyuan 's Hy4-preview runs in vLLM from day 0, verified on NVIDIA GPUs. 🎉 - 770B total, 49B active, 256 routed experts plus one shared - 1M context, but each query attends to just 2048 tokens - Only 21 of the 78 layers compute their own sparse index, the other 57 reuse one - A 10B MTP layer ships inside the checkpoint, 0.7B of it active, draft depth 3 Tencent's HPC-Ops attention and MoE kernels have been in vLLM main since Hy3. VLLM_ENABLE_HPC_OPS=1 vllm serve tencent/Hy4-preview-FP8 -tp 8 Thanks @TencentHunyuan for the preview weights! 🙌 recipes.vllm.ai/tencent/Hy4-pr… yZb 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 20 👀 1090 📊 2 ⚡

#Hy4-preview#vLLM#Tencent#MoE#sparse attention

Keep reading

Recent stories with the same tag or section
ModelsBuildersSelected17:26
vLLM Ships Day-0 Support for Sage-A1.5

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.

#Sage-A1.5#vLLM#Shanghai AI Lab#open-source models
官方账号vLLM@vllm_projectSource
ModelsBuildersSelected17:09
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