10-14-2026, 02:40 PM
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around vLLM and 4090.
Would rather learn from your scars than collect my own all at once.
I care more about stability than squeezing the last possible tokens/sec out of it.
The part that surprised me was how much the boring details mattered more than the model choice.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around vLLM and 4090.
Would rather learn from your scars than collect my own all at once.
I care more about stability than squeezing the last possible tokens/sec out of it.
The part that surprised me was how much the boring details mattered more than the model choice.
throughput matters, but tail latency matters too