AI / LLM Deployment & Operations on Linux
Private deployment, tuning and operations of mainstream open-source LLMs such as DeepSeek, Qwen and Llama.
Learn moreFull coverage of mainstream operating systems — Ubuntu, RedHat, CentOS, Kylin, UOS, openEuler and more — plus managed operations, Kubernetes private cloud and AI/LLM deployment & operations. 24/7 technical support.
A portfolio of 33 professional services across the full lifecycle of your IT infrastructure — operating systems, software development, managed operations, cloud-native and AI services.
Private deployment, tuning and operations of mainstream open-source LLMs such as DeepSeek, Qwen and Llama.
Learn moreRun open-weight LLM inference inside your own GPU environment, with both vLLM and SGLang supported. Data stays in-house, costs stay under control, and the OpenAI-compatible interface lets chat, RAG and agent workloads move over smoothly.
Learn moreCustom AI agent development, system integration and ongoing operations built around your business scenarios.
Learn morevLLM deployment and tuning built on PagedAttention — maximise per-GPU concurrency and utilisation across NVIDIA and AMD accelerators for high-throughput online inference.
Learn moreSGLang deployment and tuning built on RadixAttention — reuse KV cache across shared-prefix workloads such as multi-turn chat, RAG and agents to cut time-to-first-token and duplicated compute.
Learn moreWe benchmark vLLM and SGLang against your real traffic using tools such as GuideLLM, then deliver a selection conclusion, tuning parameters and hardware sizing advice.
Learn moreFor random freezes, reboots that hang and intermittent stalls. We preserve the scene, then use kdump/vmcore, SysRq, pstore, PSI and eBPF to reconstruct the kernel state, isolate the root cause and verify the fix. Covers RHEL, Ubuntu, SUSE, Kylin, UnionTech UOS and openEuler.
Learn moreInstallation, configuration, tuning, troubleshooting and version migration for RHEL and CentOS.
Learn moreNearly 20 years focused on Linux and open source, bringing proven production experience to your business.
Focused on Linux support since 2007, with a large body of real production case studies.
Senior Linux system engineers together with kernel and application developers, offering vendor-level diagnostic skill.
An always-on incident channel prioritises critical outages to keep business interruption to a minimum.
Four clear, transparent steps that keep every engagement efficient and under control.
We review your environment, pain points and expectations.
A tailored technical plan, a defined scope of work and a transparent quotation.
Agreed service levels and response times, deployed quickly.
Regular health checks, proactive operations and on-call technical support.
The latest from the Linux ecosystem, cloud native and AI.
From 2007 to 2025, Shanghai Hanshui Information Technology Services Co., Ltd. has gone through nearly two decades, always focused on Linux and open source technical services.
As the Xinchuang (China's IT-application-innovation push) industry advances, adapting software to domestic operating systems has become an important issue in enterprise IT build-outs.
With recently having received a review sample of the GMKtec EVO-X2 mini PC powered by the AMD Ryzen AI Max+ 395 "Strix Halo" SoC and pre-loaded with Microsoft Windows 11 Pro, I took the opportunity to see how the AMD Ryzen AI Max+ performance is comparing between Windows 11 and Ubuntu 26.10 Linux on a range of workloads from gaming to AI and creator applications.
Separate from the existing AMDXDNA accelerator driver in the Linux kernel for Ryzen AI NPUs, on Wednesday AMD posted patches for the new AMD AI Engine "AIE" accelerator driver.
After running weeks behind schedule due to PostgreSQL developers being overwhelmed by AI/LLM-led bug reports and security issues, PostgreSQL 19.0 managed to finally ship today.
AMD and Unsloth announced today that local NPU inference is now available for Unsloth Desktop, starting with the AMD Ryzen AI NPUs of XDNA 2 and later.