★ Featured: Transformer Math & CPU SLM Lab Series
50 interactive labs covering matrix multiplication, softmax, attention, KV cache, gradient flow, CPU memory budget, and the full SLM-on-CPU lifecycle. Paired with 50 deep-dive articles.
Explore all 50 labs →AI / ML / Transformers 75 labs
Transformer Math & CPU SLM ★
50Matmul, softmax, attention, KV cache, training, CPU mechanics, sampling.
LLM Visualizations
10Original deep-dives into transformer internals (tokenization, attention, QKV, softmax).
Large Language Models
5Temperature, top-k/p, KV cache memory, speculative decoding, attention masks.
Transformer Internals
5Multi-head attention, positional encoding, FFN, MoE routing, RMSNorm.
General AI
5Embedding similarity, gradient descent, k-NN, decision boundaries, RAG pipeline.
Quantization
5FP16/INT8/INT4, SmoothQuant outliers, GGUF format, perplexity vs bit-width.
MCP Protocol
5Message flow, tool registry, capability negotiation, server lifecycle, OAuth.
Distributed Systems & Infrastructure 35 labs
Distributed Systems
5Raft election, gossip spread, vector clocks, quorum reads/writes, partition tolerance.
Apache Cassandra
5Token ring, consistency levels, compaction strategies, tombstones, hinted handoff.
System Design
5Rate limiter, circuit breaker, load balancer, cache patterns, sharding.
Databases
5B-tree, MVCC, replication lag, connection pooling, pgvector ANN.
Streaming Systems
5Kafka partitions, consumer lag, exactly-once, stream-table duality, backpressure.
Concurrency
5Producer-consumer, lock contention, work stealing, race conditions, virtual threads.
Observability
5SLO burn rate, percentile latency, trace sampling, alert fatigue, golden signals.
System Simulations
5Token bucket, ring buffer, consistent hashing, TCP congestion, ABR ladder.