22 points | by sanchitmonga22 3 hours ago
3 comments
curious how the token/$ on trainuim compare to nvidia chips and amd. is the future "chipless" inference?
Tokens per minute is a strange metric, I usually see tok/s. A per-second figure would be more accessible in comparing this to alternatives.
how does this compare with sglang
curious how the token/$ on trainuim compare to nvidia chips and amd. is the future "chipless" inference?
Tokens per minute is a strange metric, I usually see tok/s. A per-second figure would be more accessible in comparing this to alternatives.
how does this compare with sglang