llm-d on Kubernetes: Prefill/Decode Disaggregation for LLM Inference
llm-d explained: disaggregated prefill and decode, KV-cache-aware routing and vLLM on Kubernetes, with cost math, an install path and where it beats a plain vLLM deployment.
vLLM 0.28 to 0.30 Migration: Model Runner V2 Default, Breaking Changes
Upgrading vLLM 0.28 to 0.30: Model Runner V2 is now default, MRV1 removal targeted for v0.32, new flags, removed env vars and a safe rollout checklist.
vLLM vs SGLang vs TensorRT-LLM in 2026: The Serving Engine Pick
vLLM, SGLang, and TensorRT-LLM compared for 2026 production LLM serving: throughput, KV-cache handling, and which to pick by workload.
AI Inference Cost Optimization: GPU FinOps in 2026
An AI inference cost optimization decision record: continuous batching, KV-cache, quantization, speculative decoding, spot GPUs, and autoscaling the inference path.
vLLM Cost Economics: 2026 Deep Dive on $/Million Tokens
A practical 2026 deep dive on vLLM cost economics — KV cache, paged attention, speculative decoding, and dollar-per-million-tokens math.
KV Cache Optimization for LLM Inference: A Deep Dive
KV cache optimization for LLM inference — PagedAttention, quantization, prefix caching, and eviction, with the memory math behind each technique.