10-18-2026, 02:16 AM
This keeps coming up in conversation so I figured I'd start a thread.
One thing I keep noticing is that people underestimate KV cache pressure until they actually try to run this stuff for more than one afternoon.
Wondering if this is just where the whole space is heading now.
I care more about stability than squeezing the last possible tokens/sec out of it.
One thing I keep noticing is that people underestimate KV cache pressure until they actually try to run this stuff for more than one afternoon.
Wondering if this is just where the whole space is heading now.
I care more about stability than squeezing the last possible tokens/sec out of it.
measure twice, benchmark three times