Why do they need to run benchmarks to confirm performance? Can't they run an example prompt and verify they get the exact same output token probabilities for all prompts? The fact that they are not doing this makes me suspicious that they are in fact not doing the exact same thing as vLLM.
It is also a bit weird that they are not incorporating speculative decoding, that seems like a critical performance optimization, especially for decode heavy workloads.
> Can't they run an example prompt and verify they get the exact same output token probabilities for all prompts?
You don’t even get that with GPUs in general, or really floating point in general.
The Art of Computer Programming. Volume 2: Seminumerical Algorithms section 4.2.2 with explain where it loses floating addition associativity property.
> However, as the name “batch-invariant” suggests, the technique is currently limited to handling variations related only to the batch dimension, making it robust to continuous batching and other batch-size–related changes, but not to other forms of nondeterminism like changing the TP sizes or GPU types.
OK... we need way more information than this to validate this claim! I can run Qwen-8B at 1 billion tokens per second if you don't check the model's output quality. No information is given about the source code, correctness, batching, benchmark results, quantization, etc. etc. etc.
Every example like this makes it obvious that you can now use ML-like optimization approaches on well-specified, very-well-tested software problems with a clear optimization goal. Keep if it improves the objective while maintaining correctness, discard if it doesn't. AI-descent strikes again.
Maybe I should learn more about ML to have a better instinct on optimization methods in general, so I can actually build AI optimizers like these.
13 comments
[ 3.2 ms ] story [ 48.1 ms ] threadIt is also a bit weird that they are not incorporating speculative decoding, that seems like a critical performance optimization, especially for decode heavy workloads.
Wouldn’t speculative decoding decrease overall throughput, but optimise (perceived) responsiveness?
You don’t even get that with GPUs in general, or really floating point in general.
The Art of Computer Programming. Volume 2: Seminumerical Algorithms section 4.2.2 with explain where it loses floating addition associativity property.
Apartness relations are another possible lens.
https://arxiv.org/abs/2506.09501
Maybe I should learn more about ML to have a better instinct on optimization methods in general, so I can actually build AI optimizers like these.
What's the post request latency of this part? What the ftt?