31 posts tagged with "performance"

The vector index your team picked was benchmarked on a workload that doesn't exist in production. Every public ANN benchmark — VIBE, ann-benchmarks, the comparison table on the database vendor's landing page — runs queries sampled uniformly from the corpus, so every neighbor lookup costs roughly the same and every shard sees roughly equal load. Real retrieval traffic does not look like that. It looks Zipfian: a small fraction of queries (today's news, the trending product, the recurring support intent, the few hundred questions a customer support team gets all day) hits a small fraction of embeddings a hundred times more often than the median. The benchmark says HNSW recall is 0.97 at 50ms p99. Production says one shard is melting and the rest are bored.

The mismatch is not a tuning problem. It's that vector retrieval inherits the access-skew profile of every other database workload, and the indexes the field has standardized on were not designed with that profile in mind. The cache layer your KV store gets for free — the OS page cache warming up the rows you read most often, the LRU on a hot key — does not exist for ANN, because the graph is walked in graph order, not access order. The hot embeddings stay cold in memory because the search algorithm's traversal pattern looks random to the page cache, and your "popular" cluster lives on a single shard whose CPU runs hot while the rest of the fleet idles.

A user reports "the assistant felt slow this morning." The on-call engineer pulls up the flame graph, sorts tool calls by duration descending, finds the slowest one — a 2.1-second vector search — optimizes it down to 900ms, ships the fix, and marks the incident resolved. A week later the same complaint arrives. The vector search is still 900ms. But the end-to-end latency on that query type has actually gotten worse. Nothing in the flame graph explains why.

This is what happens when an engineer debugs a tree on the line axis. Agent latency is not a waterfall of sequential steps — it is a nested tree of planning calls, tool subtrees, parallel fan-outs, retries, and recursive sub-agents. When the budget is structural but the tooling treats it as linear, local optimizations miss the actual violation, which lives in how time is distributed across branches, not how long any single call takes. You can make every leaf faster and still ship a p99 that is getting worse.

Open any 2024-era AI feature's trace and the model call is the whale. Eight hundred milliseconds of generation surrounded by a thin crust of retrieval, auth, and a database lookup rounding to nothing. Every architecture decision that year — the caching, the prefetching, the streaming UX — was designed around hiding that whale.

Now pull the same trace for the same feature running on a 2026 inference stack. The whale is a dolphin. A cached prefill returns the first token in 180ms. Decode streams at 120 tokens per second. The model is no longer the slow node. Your own infrastructure is, and most of it hasn't noticed.

This reordering is the most important performance shift of the year, and it's the one teams keep under-reacting to. The p99 floor on an AI request is now set by the feature store call, the auth middleware, and the Postgres lookup that was always that slow — nobody just cared when the model was taking nine-tenths of the budget.

Your users don't have a stopwatch. They have feelings. And those feelings diverge from wall-clock reality in ways that matter enormously for how you build AI interfaces. A response that appears character-by-character over three seconds will consistently feel faster to users than a response that materializes all at once after one second — even though the batch system is objectively faster. This isn't irrational or a bug in human cognition. It's a well-documented perceptual phenomenon, and if you're building AI products without accounting for it, you're optimizing for the wrong metric.

This post breaks down the psychology behind latency perception, the metrics that actually predict user satisfaction, the frontend patterns that exploit these perceptual quirks, and when streaming adds more complexity than it's worth.

If you've profiled an AI agent that felt inexplicably slow, chances are you found a waterfall. The agent called tool A, waited, then called tool B, waited, then called tool C — even though B and C had no dependency on A's result. You just paid 3× the latency for 1× the work.

This pattern is not an edge case. It's the default behavior of virtually every agent framework. The model returns multiple tool calls in a single response, and the execution loop runs them one at a time, in order. Fixing it isn't complicated, but first you need a reliable way to identify which calls are actually independent.

Your Black Friday traffic spike arrives. Conventional API services respond by spinning up more containers. Within 60 seconds, you have three times the capacity. The autoscaler does what it always does, and you sleep through the night.

Run an LLM behind that same autoscaler, and you get a different outcome. The new GPU instances come online after four minutes of model weight loading. By then, your request queues are full, your existing GPUs are thrashing under memory pressure from half-completed generations, and users are staring at spinners. Adding more compute didn't help — the bottleneck isn't where you assumed it was.

AI inference workloads violate most of the assumptions that make reactive autoscaling work for conventional services. Understanding why is the prerequisite to building systems that survive traffic spikes.

Your GPU dashboard is lying to you. At 60% utilization, your inference cluster looks healthy. Users are experiencing 8-second time-to-first-token. The on-call engineer checks memory — also fine. Compute — fine. And yet the queue is growing and latency is spiking. This is what happens when you apply traditional capacity planning to LLM workloads: the metrics you trust point to the wrong places, and the actual bottleneck stays invisible until users start complaining.

The root problem is that LLMs consume a fundamentally different kind of resource. CPU services trade compute and memory. LLM services trade tokens — and tokens don't behave like requests.

You swap your expensive LLM for a faster, cheaper distilled model. Latency goes up. Costs increase. Quality degrades. You roll back, confused, having just spent three weeks on optimization work that made everything worse.

This isn't a hypothetical. It's one of the most common failure modes in production AI systems, and it stems from a seductive but wrong mental model: that optimizing a component optimizes the system.

You're running an LLM-powered application and your p99 latency is 4 seconds. You've tuned your prompts, reduced output length, and switched to streaming. The number barely moves. The problem is not your code — it's physics and queuing theory operating inside a black box you don't own.

Every inference provider makes dozens of architectural decisions that determine your application's performance ceiling before your first API call. KV cache eviction policy, continuous batching schedules, chunked prefill chunk size — none of this is in the docs, none of it is configurable by you, and all of it shapes the latency and cost curve you're stuck with.

This post explains what's actually happening inside inference infrastructure, why it creates an unavoidable latency floor, and the handful of things you can actually do about it.

Most teams decide to use on-device LLM inference the same way they decide to rewrite their database: impulsively, in response to a problem that a cheaper solution could have solved. The pitch is always compelling—no network round-trips, full privacy, zero inference costs—and the initial prototype validates it. Then six months post-ship, the model silently starts returning worse outputs, a new OS update breaks quantization compatibility, and your users on budget Android phones are running a version you can't push an update to.

This guide is about making that decision with eyes open. On-device inference is genuinely the right call in specific situations, but the cost structure is different from what teams expect, and the production failure modes are almost entirely unlike cloud LLM deployment.

Most AI engineering teams have the same story. They start with a hard problem that genuinely needs an LLM. Then, once the LLM infrastructure is in place, every new problem starts looking like a nail for the same hammer. Six months later, they're calling GPT-4o to check whether an email address contains an "@" symbol — and they're paying for it.

The "just use the model" reflex is now the dominant driver of unnecessary complexity, inflated costs, and fragile production systems in AI applications. It's not that engineers are careless. It's that LLMs are genuinely impressive, the tooling has lowered the barrier to using them, and once you've built an LLM pipeline, adding another call feels trivially cheap. It isn't.

Your AI feature ships. Response times look reasonable in staging. A week later, production starts throwing mysterious p99 spikes — latency jumps from 800ms to 8 seconds under moderate load, with no GPU pressure, no model errors, and no obvious cause. You add more replicas. It doesn't help. You profile the model server. It's fine. You add caching. Still no improvement.

Eventually someone checks the database connection pool wait time. It's been sitting at 95% utilization since day three.

This is the most common category of AI production incident that nobody talks about, because connection pool exhaustion looks like model slowness. The symptoms appear in the wrong layer — you see high latency on LLM calls, not on database queries — so the diagnosis takes days while users experience degraded responses.