I'm currently trying to write an inference engine that combines the benefits of llama.cpp (one binary deployment, good support for heterogenous non-datacenter compute, wide quantization support) with the benefits of vLLM/SGlang (things like proper paged attention for better VRAM utilization and high concurrency).

Datacenter hardware is expensive and there's shortage of it but llama.cpp is slow/unoptimized for concurrent use, while vLLM/SGLang easily crash on non-common setups (things like, if you do pipeline parallelism for RTX5090+RTX4090, they will randomly crash with RAM caching enabled or select wrong kernels because they usually assume that every rank is the same device type; they also don't support Q5-Q6).

For me what's most interesting is to optimize inference for lack of good datacenter hardware and how to optimize for it best. I've been running an AI server in the office, and so far I've find these techniques most important for concurrent use on cheap hardware: pipeline parallelism (to accomodate for PCie), RAM caching (to quickly restore contexts into VRAM), speculative decoding (including domain-specific ngrams, they already can speed up code generation considerably without the overhead of a draft model), good kernels highly optimized for a specific device, support for Q5-Q6 (almost as good as Q8), FP8 contexts (more context to fit), paged attention (for better VRAM utilization), prefix caching, continuous batching (this is the default everywhere).

So far the main bottlenecks have been llama.cpp's poor VRAM utilization for contexts (you either have fixed-size slots, or use unified KV cache where each request attends to attention from all other requests and then unnecessary portions of attention are masked out), and lack of decode/prefill segregation: when a request starts prefilling a long context, all decoding threads slow down to like 5 tok/sec. On the other hand, vLLM/SGLang feel superbuggy if you don't run them on some officially approved node like 8xH200

> Speculative decoding is the process of guessing which tokens a model might generate, then validating those guesses.

As a computer engineer, it’s always interesting to see optimizations applied at different levels of the stack.

Speculative execution became pretty popular in the 90s, eventually used in basically every x86 design.

Then in the mid-2000s the Speculator[0] paper brought that concept to distributed systems, which we’re still seeing work on[1][2].

Everything old is new again (:

[0]https://www.cs.princeton.edu/courses/archive/fall07/cos518/p...

[1]https://www.usenix.org/system/files/osdi25-shen-weihai.pdf

[2] https://www.microsoft.com/en-us/research/publication/distrib...

This article describes what is usually called a Pareto frontier: the best known achievable trade-offs between two (or more) optimization goals. "Efficient frontier" in common usage seems to be specifically a Pareto frontier for financial risk versus return of an investment portfolio. Even outside of finance, points on a Pareto frontier are called Pareto optimal or Pareto efficient. A Pareto frontier is sometimes shown with more than two dimensions, although usually people will pick just two for simplicity.

Within LLMs, and even inference naturally, there are many other potential parameters that one might optimize: Unsloth typically shows a Pareto frontier for size of a quantized model versus KL divergence. Others trade total concurrent tok/s against single-stream tok/s. KV cache size, context length and context coherency are other trade-offs that are closely related to inference. Total intelligence is usually a defining characteristic of a "frontier model", with cost (per token or task) as a salient trade-off. Cost is one parameter that is implicitly fixed by the "throughput versus latency" analysis: using a GB300 versus Radeon R9700 moves the curve enormously and probably changes the shape of it. Lots of threads here argue over local vs cloud inference regarding cost efficiency, often with privacy and control as competing objectives.

this is a nice and concise writeup. what's striking to me is that these techniques really have not changed in /years/. sure, precision has become slightly lower, spec decoding acceptance has gotten slightly better and the complexity of parallelism is trickier with mixture of experts. but no new concepts in a very long time!

the absolute most impactful improvements for inference comes at architecture design time. I firmly believe everyone who cares about impacting model efficiency should look there

I think we can soon include "recursive depth" strategy that Astra is employing, which (I suspect) is using recursive internal state changes in the transformer as opposed to full forward-pass + sampling which has traditionally been the case with thinking/CoT. Similar method was used here (but different context - encoding tools inside the transformer weights for fast execution): https://www.percepta.ai/blog/can-llms-be-computers

2026 has been the year where spec-dec has matured, it has been adopted by all big OSS engines and i'm sure it's present in quite a lot of inference providers as the default

I feel like P/D dissaggregation will be the next big one for providers, as prefill tends to be compute bound while decode mem bound which I guess each will have a different type of node

Quantization and speculative decoding unlocked major savings for our smaller models. Still chasing that ideal cost/performance ratio.

   Inference techniques either move a deployment along the latency–throughput frontier or push the entire frontier out, creating more efficiency to allocate.

This is a tautology. You can say that with anything. Gastronomy techniques will make a previous recipe better, or create a new recipe better than others, or a mix of both.

My daily struggle is trying to make a 7B model respond in under 500ms without breaking the bank. This hits home.

How do you know for sure that you stay on an efficient frontier when you change a parameter?

I think this presentation says more about what knobs you can turn and in what direction the outcome will move (it may be worse than a competitor) than it says about frontiers.

My RTX 3090 is still laughing at my attempts to run 70B models efficiently.

You know what I'm curious about? Whether you have brand guidelines inside the company, a Claude skillset, or the blog post author makes the charts in line with the brand colours and so on.

Nice read. I was wondering what can one do to get into inference engineering as simple theoretical knowledge is not sufficient and switching profiles is tough for someone with years of experience.

"the efficient frontier" is an important landmark of (investment) portfolio theory. It proves/explains/illustrates how you can combine selections from a diffuse cloud of individual investments and still land on a frontier that is better than any of your individual choices. It's the entire basis of "diversify your portfolio".

The efficient frontier of LLM inference is a line, not a frontier.

this is a frontier:

https://upload.wikimedia.org/wikipedia/commons/e/e1/Markowit...

no matter how good is something a smart person writes down, a pleb will come along and try to hang on its coattails.

If you want to steal an idea for this, steal indifference curves, they'd make more sense.

The author does not deeply mention that quality/intelligence is a third dimension here in addition to throughput and latency, and the frontier is jagged so quality and intelligence require bespoke benchmarks to evaluate tradeoffs for speed and cost.

good recap on the recent inference techniques!