Work2026某大型制造业集团Domestic inference resource pool

Domestic AI inference resource pool

Build group-level AI infrastructure across compute, network, and storage, enabling unified management, scheduling, and service delivery.

Manufacturing group / Enterprise AI platform国产化算力
Domestic AI inference resource pool
Context

Domestic inference resource pool

Manufacturing group / Enterprise AI platform · 某大型制造业集团 · 2026

The manufacturing group spans R&D, production, quality, supply chain, equipment operations, and digital operations, and needed a unified AI infrastructure capability.

The customer planned to build a domestic AI inference resource pool for headquarters, factories, departments, and production systems.

The pool needed to support models such as ChatGLM, Baichuan2, LLaMA 34B, and LLaMA2 13B/70B, while integrating with the group cloud management center and AI platform.

Delivery path

From connect to ship, in four steps

01

Compute pool

Deploy domestic inference servers as a centralized compute pool.

02

Network

Build separated network planes for low-latency, high-throughput communication.

03

Storage

Deploy distributed storage for models, samples, inference, and production data.

04

Management

Integrate with hybrid-cloud management and the group AI platform for unified management and scheduling.

Full project record
01

Customer profile

A unified domestic AI inference resource pool for a large manufacturing group, supporting multiple large models and group-level AI platform operations.

02

Needs

The manufacturing group spans R&D, production, quality, supply chain, equipment operations, and digital operations, and needed a unified AI infrastructure capability. The customer planned to build a domestic AI inference resource pool for headquarters, factories, departments, and production systems. The pool needed to support models such as ChatGLM, Baichuan2, LLaMA 34B, and LLaMA2 13B/70B, while integrating with the group cloud management center and AI platform.

03

Solution

The solution was designed across compute, network, and storage to build a high-performance domestic AI resource pool for large-model inference.

04

Impact

17.5PFLOPS FP16 AI compute; 200GE RoCE parameter network; 1024G Per-node HBM memory; 统一调度 Unified group-level scheduling

Impact

Numbers that prove value

0PFLOPS
FP16 AI compute
0GE
RoCE parameter network
0G
Per-node HBM memory
统一调度
Unified group-level scheduling
Domestic inference resource pool

Bring this capability into your business

Key capabilitiesKUNLUN compute clusterHigh-speed interconnectMulti-plane networkingSpine-Leaf and M-LAG
OURYUN · Connect · Govern · Deploy · Ship ·