2026

• posts Jun 7 vLLM Request Lifecycle: From OpenAI API to One Forward Pass
• posts Jun 5 Prefill vs Decode: Why One Model Has Two Very Different Bottlenecks
• posts Jun 5 LLM Attention Kernels and GPU Primitives
• posts Jun 5 LLM Quantization and Low-Precision Serving
• posts Jun 5 LLM Inference Lab Reports: Experiments and Benchmarks for Serving Systems
• posts Jun 4 vLLM / SGLang Source Reading: From Request to Forward Pass
• posts Jun 4 LLM Inference Internals: Core Mechanisms for Serving Engines
• posts Jun 1 A Survey of LLM Quantization: From Linear Quantization to Codebooks
• posts May 28 From Absolute Positional Encoding to RoPE: Why Position Can Be a Rotation
• posts May 27 Estimating Compute and Memory Requirements for LLM Training and Inference
• posts May 23 Agent Skill Management: Turning AI Assistants from Clever to Reliable
• posts Apr 22 Disaggregated Prefill: Splitting Compute Across Machines
• posts Apr 22 Prefix Caching: Reusing KV Cache Across Requests
• posts Apr 22 Chunked Prefill: Slicing the Prefill to Protect Decode Latency
• posts Apr 22 Continuous Batching: Scheduling at Iteration Granularity
• posts Apr 22 Paged Attention: Virtual Memory for the GPU
• posts Apr 21 Online Softmax: Tiling for Arbitrarily Large Rows
• posts Apr 20 Why KV Cache Works in LLM Inference
• posts Apr 20 Fused Softmax in Triton
• posts Apr 19 SSH Port Forwarding: Local and Remote Tunnels Explained

• 1
• 2
• 3
• 4