Tencent Hunyuan's Hy4-Flash engine PR reveals tensor parallel, MTP drafts, CPU expert lane
TencentHunyuan · x · 2026-11-19
Tencent Hunyuan retweeted a GitHub PR bringing Hy4-Flash to the open-source Project Maya inference repo with a dedicated maya-hy4 engine (NVIDIA, Linux).
Key details: the model has 42 layers plus an MTP block, MLA attention (512-token sliding window, 12 layers with an indexer), 512 routed experts with top-16 routing, 4 hyper-connection streams, and Engram n-gram lookups on 4 layers. The engine supports tensor parallelism (--tp auto|N|0), MTP draft inference, and a CPU expert lane; packing from AngelSlim's GGUF writes geometry/index/tokenizer without copying weights, and the server supports chat, thinking with effort levels, and tool calls.
More from Infra
- Linux Mint website goes dark, showing hosting placeholder pages — kingslyj · 2026-11-19
- Commentator calls Jensen Huang's China compute claim bullshit: won't outpace rest of world — teortaxesTex · 2026-11-19
- TRELLIS.2 CUDA kernels on HF Kernels cut BVH build from 7.1s to 5ms — ariG23498 · 2026-11-19
- OpenCode fix cuts GPT-6.2 uncached input per step from ~14,000 tokens to 3 — victor_explore · 2026-11-19
- Voters blocked 40 of 41 data center ballot measures; Alphabet pledges $1B in local spending — rohanpaul_ai · 2026-11-19
- Qwen3.8-27B Q4 on an 8GB RTX 4060 scores 29/30 on AIME 2026 with three no-fine-tune loops — Ai_Glitch_3301 · 2026-11-19