Your MoE router sends 90% of tokens to 10% of the experts. What happens to the step, and how do you fix it without hurting the model?

A router that sends 90% of tokens to 26 of 256 experts makes those ranks do nine times their share while everyone else waits. The arithmetic of the imbalance, what a capacity factor drops on the floor, why the auxiliary loss fights the model, and the bias-only balancing DeepSeek-V3 used instead.

Updated Sep 2026 · Grounded in real AI infrastructure interview loops and written to a senior-engineer editorial bar, with every number worked and every diagram hand-built.

more free answers with an account · no card

The concepts behind this question

Ranked by how closely each one overlaps this question's topic, so the first card is the thing to read if the answer above moved too fast.

Advanced

🕸️ Distributed Training🔒 Premium

Expert Parallelism for MoEA mixture-of-experts layer runs only a few of its experts per token, so the experts can be spread across GPUs and each token shipped to the ranks that hold its chosen experts. That shipping is an all-to-all in each direction, twice per layer per pass, and its cost plus the load imbalance between experts is what expert parallelism is really about.

Foundational

💻 Coding for Infra

Consistent Hashing and ShardingSplitting work across N servers with a modulo of N moves almost everything when N changes, which for a cache means throwing away almost all of it. Consistent hashing places servers and keys on a ring so adding or removing one moves only its share, and virtual nodes fix the imbalance a small ring otherwise has. In LLM serving the same structure routes requests by prompt prefix so a conversation reaches the replica already holding its cache.

Foundational

🧮 Open Weights & Serving Engines

Expert Parallel and All-to-All BackendsA mixture-of-experts model can be split two ways and the choice changes everything. Tensor parallelism shards each expert across GPUs, which keeps every GPU busy and reads every expert's shard on every token. Expert parallelism gives whole experts to whole GPUs, which reads only the selected experts but requires an all-to-all to route tokens to them and back. The all-to-all is the cost, its backend is a configuration choice matched to the interconnect, and expert load imbalance is what actually limits the result.

Advanced

📐 AI Systems Design🔒 Premium

Request Routing and Load Balancing for LLMsA load balancer for stateless web services spreads requests evenly and is done. A router for LLM replicas has two things a web balancer never had to think about: each replica holds a cache (the KV pages of recent prefixes) that makes some replicas far cheaper than others for a given request, and each request costs a wildly different amount, so counting connections is meaningless. This page builds the router that handles both: prefix-aware placement with load-aware fallback, cost-aware queue estimates, session affinity, and the failure handling when a replica restarts and its cache is gone.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackYou have 16,384 H100s and a 405B dense model. Choose the parallelism layout and justify the order of the axes.Next in this trackExplain mixed-precision training. Why does fp16 need loss scaling and bf16 not, why keep fp32 master weights, and what changes with fp8?Next in this trackYour training run is at 60% of the step time you projected. How do you find out whether it is compute, memory, network or I/O?

FEDITOR'S NOTE

Scored on quantifying the step-time damage, on knowing that capacity limits trade dropped tokens for bounded time, and on explaining why a per-expert bias outside the gradient path balances without distorting the gate.

DISCUSSION · 0

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