← Coding for Infra / 33

hardNew

Implement a LoRA forward pass and merge two adapters without inventing cross terms

Follow the matrix shapes through a low-rank update. Verify merged inference numerically and show why multiplying sums of adapter factors gives the wrong weights.

Updated Sep 2026 · Learn how AI infrastructure works through explanations, worked examples and diagrams, then practise applying it to interview questions.

Follow the matrix shapes through a low-rank update. Verify merged inference numerically and show why multiplying sums of adapter factors gives the wrong weights.

The full answer is part of Premium. A free account includes more answers in each topic, but does not unlock this one.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 303 remaining answers · ₹2,000 / $25

The concepts behind this question

Use these concept explanations to review the ideas behind this question.

🧮 Open Weights & Serving Engines🔒 Premium

Pretraining, Fine-Tuning and DistillationUnderstand how a base model becomes a useful application model. Separate training objectives from LoRA and quantization, compare distillation with retrieval, and choose the smallest intervention supported by your evaluation.

🚀 Inference & Serving🔒 Premium

Multi-LoRA ServingMulti-LoRA serving applies different adapters to a shared base model. It saves weight memory while adding adapter loading, scheduling and isolation requirements.

📐 AI Systems Design🔒 Premium

Multi-Tenant Fine-Tuning ServiceA fine-tuning service turns a tenant’s dataset into an evaluated model or adapter. Its pipeline must protect data while scheduling training and serving the result efficiently.

💻 Coding for Infra

The GPU Credit Scheduler PatternA credit scheduler admits jobs without overspending an account’s balance. Clear state transitions make priority, cancellation and refunds easier to implement correctly.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackImplement scalar autograd and prove that a shared input receives every gradient contribution Next in this trackImplement a bounded request log with timers that remain correct under concurrency Next in this trackImplement a thread-safe in-memory KV store with snapshot transactions and TTL

DISCUSSION · 0

No comments yet — be the first to share your approach.