Surpassing vLLM with a Generated Inference Stack
infinity.incDoes it support page attention like vLLM though? Without that they will run into memory fragmentation quickly.
Yes, great question!
The system started without paged attention, and recreated its own paged attention implementation automatically once it realized it was a bottleneck.
Pretty cool!
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.
Yes, speculative decoding will make both us and VLLM faster, but we believe it would be a relatively even bump on both sides, so we didn't include it in this comparison. Worth another test!
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.
We validate with MMLU and Hellaswag presently, and are getting this independently verified by a 3rd party.
We have considered open-sourcing some of our optimized inference libraries in the future, but have not yet come to a decision on this.
Also if you need a rough intuition as to why this is possible: it's because this entire inference stack was built for exactly one model, and thus we can really tune the entire framework accordingly.
Luke: Do you have benchmarks for BF16?
Unfortunately, not at present; we went for FP8 because we believed it was generally the best tradeoff of quality and speed. Allowed faster iteration as well.
We believe our improvements would hold on BF16, but let me check.