hygon

Heterogeneous GPU Sharing on Kubernetes

国产加速卡-海光DCU实战（大模型训练、微调、推理 等）

Reproducible single-GPU Qwen3.6-35B-A3B W8A8 inference tuning for Hygon K100AI (gfx928) on vLLM 0.18.1.

K100AI 模型部署实践 —— 海光 K100-AI 上大模型的成功配置线拉起包（当前：Qwen3.8-27B 六条精选线；持续更新）

海光 K100 LC（gfx926）上从零自研的 Qwen3.8-27B 推理运行时：RT4 权重格式、int4 算子、MTP3 投机解码、本地视觉塔与 OpenAI 兼容服务

Unsloth Studio deployment for Hygon K100-aiDCU on DTK 26.04

MiniMax H3 INT8 ConvRot optimization and dual-K100AI QKV/Attention inference for Hygon K100AI (gfx928)

dsh plugin for scnet.cn

Open-source model serving and heterogeneous GPU management platform for enterprise private AI. NVIDIA / Ascend / Cambricon / Hygon, unified through OpenAI-compatible APIs.

Agent skill for working on SCNet clusters

A ~2,000-line miniature of vLLM v1 with a vLLM-style Platform/op-family hardware abstraction layer. One engine, four backends: NVIDIA CUDA, Hygon DCU (DTK/HIP), Ascend NPU, Moore Threads MUSA. Real continuous batching, paged KV cache, TP, CUDA graph — runs Qwen3 end-to-end

Terminal monitor for Hygon DCU (hy-smi) with nvtop-style scrolling curves