47 points | by charles_irl 10 hours ago ago
2 comments
> 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
> Gallia est omnis divisor in partes tres.
OCD-driven fix: The correct Latin quote is "Gallia est omnis divisa in partes tres".
> 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
> Gallia est omnis divisor in partes tres.
OCD-driven fix: The correct Latin quote is "Gallia est omnis divisa in partes tres".