29 related articles

An in-depth look at the real daily work of data scientists, MLEs, and MLOps engineers — covering responsibilities, essential tools, and career paths to help you find your direction in AI.

Detailed analysis of Kimi K3 quantization deployment options, comparing q4 vs q8 storage requirements, precision trade-offs, and hardware configurations for local self-hosting.

In-depth review of Panel AI v1.1.1: second-level installation, no-public-IP networking, batch compute cluster management. Learn how enterprise AI on-premises deployment barriers are dramatically lowered.

Benchmarking 4×V100 16G PCIe vs. 2×V100 32G SXM adapter for local LLM inference. Prefill speed, decode speed, power limits, and bandwidth bottlenecks analyzed.

Claude Opus 5 launches next week; Alibaba Qwen integrates into Apple Intelligence for Chinese users; 27B on-device model compressed to 3.8GB; open-source models narrow gap to closed-source by 3.3%.

A deep dive into vLLM's five core features — KV cache management, continuous batching, and distributed inference — plus a full setup guide for deploying DeepSeek on a cloud server.

Deploy DeepSeek-V4-Flash DSpark on 8× H20-141G using GPUStack's SGLang backend on Day 0. Full walkthrough of Web UI config, parameter tuning, and 200 tokens/sec benchmark results.

ExLlamaV3 v1.0.0 releases with lossless KV cache quantization via kernel fusion, removal of flash-attention-2/xformers, major GEMM/GEMV gains, and broader tensor parallelism support.

A comprehensive decision framework for production LLM deployment: model selection (open-source vs. API), GPU VRAM configuration, and inference engine comparison including vLLM and TensorRT-LLM.

A deep dive into distributed AI systems engineering: data/model/tensor parallelism for training, KV cache, quantization, elastic scaling for inference, and cloud deployment with Kubernetes, Ray, and DeepSpeed.

A deep dive into Distributed AI Systems: a new book distilling 10 years of AI engineering experience covering distributed training, inference optimization, and production model serving.

From pressing Enter to the first character appearing, what happens inside an LLM? This article breaks down autoregressive generation, KV cache acceleration, and decoding strategies like temperature, Top-k, and Top-p.

A deep dive into the five genuinely tough challenges of production MLOps: fault-tolerant training on Spot instances, cross-team GPU scheduling, data reproducibility, model observability, and inference cost optimization.

SlickToken is a GPU fleet and agentic workflow planning tool for AI teams, supporting offline simulation, load testing, and capacity planning—no internet required to protect enterprise data.

An in-depth analysis of the vLLM inference framework's core principles: from the meaning of throughput (tokens/s), to the bottlenecks of autoregressive generation, to KV Cache, PagedAttention, and continuous batching.

OpenAI's GPT Live full-duplex voice model, Grok 4.5 coding model with Cursor, and ByteDance's Seedream 5.0 Pro image generation launched together. A deep dive into three AI releases.

SGLang's team converted expert knowledge into agent skills, achieving 71.4% throughput gains, TTFT reduced from 456ms to 168ms. A deep dive into agent-assisted kernel optimization methodology.

A hands-on comparison of 6 open-source LLMs (DeepSeek, Qwen3, Zhipu GLM, Kimi K2, MiniMax M3, Tencent Hunyuan 3) for on-premise deployment—covering hardware cost, inference efficiency, and deployment difficulty.

Master LangChain from scratch: the three limitations of LLMs, init_chat_model unified interface config, the Message type system, and the path from LLM calls to Agent development.

AMD MI355X achieves 2,626 tokens/sec throughput running GLM5.2 at half the TCO of NVIDIA Blackwell. Deep analysis of the technical logic, ROCm ecosystem progress, and market implications.