Three types of LLM workloads and how to serve them
1–6 of 6 posts
Re: Three types of LLM workloads and how to serve them
#2> Gallia est omnis divisor in partes tres.
OCD-driven fix: The correct Latin quote is "Gallia est omnis divisa in partes tres".
Re: Three types of LLM workloads and how to serve them
#3> we recommend using SGLang with excess tensor parallelism and EAGLE-3 speculative decoding on live edge Hopper/Blackwell GPUs accessed via low-overhead, prefix-aware HTTP proxies
lord
Re: Three types of LLM workloads and how to serve them
#4> Gallia est omnis divisor in partes tres. OCD-driven fix: The correct Latin quote is "Gallia est omnis divisa in partes tres".
oof ty, willfix
Re: Three types of LLM workloads and how to serve them
#5> we recommend using SGLang with excess tensor parallelism and EAGLE-3 speculative decoding on live edge Hopper/Blackwell GPUs accessed via low-overhead, prefix-aware HTTP proxies lord
Sorry to lead with a bunch of jargon! Wanted to make it obvious that we'd give concrete recommendations instead of palaver.
The technical terms there are later explained and diagrammed, and the recommendations derived from something close to first principles (e.g. roofline analysis).
Re: Three types of LLM workloads and how to serve them
#6Very cool insights, thanks for sharing!
Do you have benchmarks for the SGLang vs vLLM latency and throughput question? Not to challenge your point, but I’d like to reproduce these results and fiddle with the configs a bit, also on different models & hardware combos.
(happy modal user btw)