#sparse-attention
- Tencent open-sources Hy4 preview, a 770B MoE flagship with 1M context Tencent Hunyuan models-llm
- Tencent open-sources Hy4 preview: 770B / 49B-active MoE with Gated DSA + iHC, 1M context, Apache 2.0 Tencent models-llm
- Tencent Hunyuan open-sources SAS sparse-attention routers trained end-to-end on Qwen3 Tencent Hunyuan research