Tencent Hy(@TencentHunyuan):🚀 We’ve open-sourced AngelSpec, an end-to-end speculative decoding framework supporting both training and deployment. On Hy3-A21B, DFly delivers a 1.98–2.40× end-to-end speedup over autoregressive decoding across tested concurrency levels from 4 to 64, with 10.5–11.8% higher throughput than DFlash. Training code and Hy3-A21B MTP/DFly drafter weights are now available: GitHub: https://t.co/6Li9K4wTFY Paper: https://t.co/BxJf0Gr3Nv Docs: https://t.co/BeFFxxsGKR Hugging Face: https://t.co/lT5tWoto1C ModelScope: https://t.co/1LNTI906EY #Hy3 #AngelSpec #OpenSource

Tencent Hy

@TencentHunyuan

Tencent's foundation model for text, image, video, and 3D generation.

参加 July 2024

8 フォロー中 45.3K ファン

Tencent Hy@TencentHunyuan

2026.07.29 12:43

🚀 We’ve open-sourced AngelSpec, an end-to-end speculative decoding framework supporting both training and deployment. On Hy3-A21B, DFly delivers a 1.98–2.40× end-to-end speedup over autoregressive decoding across tested concurrency levels from 4 to 64, with 10.5–11.8% higher throughput than DFlash. Training code and Hy3-A21B MTP/DFly drafter weights are now available: GitHub: Paper: Docs: Hugging Face: ModelScope: #Hy3# #AngelSpec# #OpenSource#