01
A cache hit is only part of the story
The first data-path checks in a tiny API lab, and the latency questions I want to ask next.
A PERSONAL SYSTEMS NOTEBOOK
Closer to
the machine.
C++, CUDA, inference & the systems underneath.
Learning by building. Understanding by measuring.
Explore the notes Merakla başlayan, notlarla büyüyen.
CURRENT ORBITC++ / CUDAInferenceReliabilityRead. Build. Repeat.
THE NOTEBOOK
Recent notes.
02
Write the question before the benchmark
A working plan for CUDA experiments: define the comparison, record the environment, and earn the conclusion.
03
A small lab, a longer attention span
Giving an old Linux laptop a clear job—and making room for experiments that outlive an SSH session.
THE PERSON BEHIND THE NOTES
I like the questions
under the abstractions.
Why did latency climb? Where did the memory go? What actually ran on the GPU? This is where I keep those questions—and the small experiments that follow.
A little about me