12 posts in total
2026
llama.cpp Workflow: Download, Convert, Quantize, and Serve Models
Compile NEFF Executables from PyTorch Code
vLLM Platform System
How the KV Cache Works in HuggingFace Transformers
Local CUDA vLLM Setup for Python-Only Development Using a Precompiled Wheel
vLLM Internals — PagedAttention and Custom Accelerator Compilation
Our Cognitive Profile and a Personal Playbook for the Agentic Era
Exporting Compute Graphs, LLM Shape Dynamics, and Serving Runtimes
Jie Liu's B-Exam: Abstractions and Optimizations for Sparse Tensor Computation on Modern Hardware
Critique of "RFSeek and Ye Shall Find: A tool for summary visualization and analysis of RFCs"