gitaskhub

Tencent Hunyuan 3 (295B MoE) on 2x NVIDIA DGX Spark: NVFP4 W4A16 + native MTP speculative decoding. First published MTP-on-GB10 numbers, full recipe, KV math, and every bring-up bug documented.

Stars · 18
Language · Shell
Ask anything about this repo to start.
Full explanation on explaingit →

By chatting or signing in you agree to the Terms and chat-message logging (revocable in History).