Skill Suites
Code-first guides on AI, DevOps, and shipping software
Real proof-of-concepts you can run today. No fluff, no filler, just working examples.
Latest articles
-
Activation Memory: Why the Forward Pass Costs More Than the Weights
Activation memory scales with batch, sequence, hidden size and depth, not parameters. The lifecycle, the quadratic attention trap, and every lever that…
-
Training Memory: The Four Tenants and the 16 Bytes Per Parameter
Why a 3 GB model needs 25 GB to train. The four memory tenants derived from first principles, where the 16 bytes…
-
LLM Fine-Tuning Explained: What Actually Changes Inside the Model
LLM fine-tuning runs the pretraining objective on your data with a loss mask. What actually changes, when to do it, and how…
-
Benchmark Your Own LLM Serving Stack: Two Measurements, One Afternoon
Run an LLM serving benchmark on your own GPU in a single afternoon: measure the hardware roofline, sweep concurrency for TTFT and…
-
Continuous Batching and PagedAttention: How vLLM Keeps a GPU Busy
Continuous batching fixes scheduling and PagedAttention fixes KV cache memory. How vLLM keeps a GPU busy, with the arithmetic and the flags…
-
The Roofline Model: Why LLM Decode Is Memory-Bound
The roofline model in one chart: why LLM decode at batch 1 uses under 1 percent of your GPU, where batching stops…
-
Attention Is All You Need, Dissected: The 2017 Figure, Box by Box
Attention Is All You Need, read box by box: the two towers, three attention blocks, cross-attention, post-norm, and what modern models kept…
-
Mixture of Experts Explained: Conditional Computation From Zero
Mixture of experts explained from zero: the router arithmetic, total versus active parameters, and the three honest caveats most explanations skip entirely.
-
The Feed-Forward Network: Where a Transformer Keeps What It Knows
The feed-forward network holds 82 percent of a transformer block. Trace W_gate, W_up and W_down by hand, six channels at a time,…
Browse by topic
- AI Use Cases40 posts
- Java & Spring15 posts
- LLM Inference11 posts
- System Design10 posts
- Hosting & SSH9 posts
- LLM Fine-Tuning3 posts
- AI Security2 posts
- Neural Networks2 posts
