Cyberpunk neon rain赛博霓虹雨夜
Vertical 1080P · 10s竖屏 1080P · 10 秒
Private deployments only · info@hanqing.com仅提供私有化部署 · info@hanqing.com
Hanqing builds and runs private GPU clusters for AI video workloads — B300, B200, H200, RTX PRO 6000 and H100 — in your data centre or a hosted one. Root stays with you.瀚擎为 AI 视频负载搭建并运营私有 GPU 集群 —— B300、B200、H200、RTX PRO 6000、H100 —— 部署在你的机房或托管机房,root 权限始终在你手里。
GPU seriesGPU 系列
5
Per-GPU memory, up to单卡显存,最高
288 GB
Memory bandwidth, up to显存带宽,最高
8 TB/s
A private GPU cluster built for video workloads. We build and run it. You own it.一套为视频负载而建的私有 GPU 集群。我们搭建和运维,你拥有它。
B300, B200, H200, RTX PRO 6000 and H100, sized to your workload and shared with no one.B300、B200、H200、RTX PRO 6000、H100,按你的负载选型,不与任何人共享。
Text-to-video, image-to-video, batch rendering and fine-tuning, tuned on your real jobs.文生视频、图生视频、批量出片与微调,按你的真实任务调优。
Weights, prompts and renders never leave your hardware. Air-gapped works too.权重、提示词与成片都留在你的硬件上,也支持完全离网。
Kubernetes scheduling, round-the-clock monitoring and a spare-parts SLA. Root stays with you.Kubernetes 调度、全天候监控与备件 SLA。root 权限始终在你手里。
Two films and five frames, all rendered on Hanqing compute.两支成片、五帧画面,全部在瀚擎算力上生成。
1080P · 21s · with sound1080P · 21 秒 · 含声音
1080P · 30s · 12 shots1080P · 30 秒 · 12 镜
Vertical 1080P · 10s竖屏 1080P · 10 秒
Vertical 1080P · 10s竖屏 1080P · 10 秒
Vertical 1080P · 6s竖屏 1080P · 6 秒
Vertical 1080P · 15s竖屏 1080P · 15 秒
Vertical 1080P · 8s竖屏 1080P · 8 秒
We built our own AI data centre to run video generation. Now we build and run yours.我们为自己的视频生成负载建了一座 AI 数据中心,现在也为你建、为你运维。
How it is delivered交付形态
What we stand up交付的技术栈
Your facility你的机房
Power, cooling, network电力 · 制冷 · 网络
GPU racksGPU 机柜
B300, B200, H200, RTX PRO 6000 and H100B300、B200、H200、RTX PRO 6000、H100
InfiniBand fabricInfiniBand 网络
Validated before handover验证通过后移交
KubernetesKubernetes 调度
Jobs routed across the fleet任务跨集群路由
Your models and API你的模型与 API
In your domain在你的域内
We audit power, cooling and network, then design racks that pass your compliance review.勘测电力、制冷与网络,输出能通过合规评审的机柜方案。
Hardware racked and cabled, then run at full load until the InfiniBand fabric passes.上架布线后满载压测,InfiniBand 网络验证通过后移交。
Kubernetes goes in, your video models land in-domain, throughput is tuned on your real jobs.部署 Kubernetes,视频模型在域内落地,按真实任务调优吞吐。
Round-the-clock monitoring, a spare-parts SLA and regular capacity reviews. Root stays with you.全天候监控、备件 SLA、定期容量复盘。root 权限始终在你手里。
Pick by workload. Delivered as a private deployment.按负载选型,私有化交付。
288GB HBM3e
Best for适用
Very large model training · inference acceleration超大模型训练 · 推理加速
180GB HBM3e
Best for适用
Large-model training · high-throughput inference大模型训练 · 高吞吐推理
141GB HBM3e
Best for适用
Large models · high-memory inference大模型 · 大显存推理
96GB GDDR7
Best for适用
Inference · video generation & rendering推理 · 视频生成与渲染
80GB HBM3
Best for适用
Model training · fine-tuning模型训练 · 微调
Swipe for more左右滑动查看更多
Routing调度
Every job goes to the GPU that fits it — by model size, resolution, duration and latency.每个任务都按模型规模、分辨率、时长和时延,路由到最合适的 GPU。
Incoming jobs任务队列
Text-to-video · 1080P · 30s文生视频 · 1080P · 30 秒Image-to-video · 1080P · 10s图生视频 · 1080P · 10 秒Brand LoRA · fine-tune品牌 LoRA · 微调Long-context inference大显存推理 · 长上下文Batch render · 200 clips批量出片 · 200 条Model training · multi-node模型训练 · 多节点Frontier model training · multi-node超大模型训练 · 多节点Incoming jobs任务队列
Pricing报价
Quoted per project. Tell us your models, cluster size and timeline.按项目报价。告诉我们你的模型、集群规模和时间表。
Private deployments, quoted per project. Write to us.私有化部署,按项目报价。欢迎来信。
Contact联系方式info@hanqing.com