BackboardIO

@BackboardIO

a new way to: inference. pre-training. post-training. quant. kerneling where no one has kerneled before.

Ottawa

BackboardIO
@BackboardIO
20m
Interactivity is how fast tokens stream once generation starts. It's the difference between an agent that feels instant and one that stutters. In AgentX, Backboard's p90 interactivity versus SGLang is up to an order of magnitude better: 12.8x in one session, 5.0x at 16 sessions. See our full results in the blog post. ow.ly/zmRx51053g1
BackboardIO
@BackboardIO
3h
Anything > 1.0X = money being left on the table.
BackboardIO
@BackboardIO
3h
Our benchmark rules are simple: Benchmark what you built, not what you built for the benchmark. Hold the model, hardware, workload, and measurement constant. Publish the failures and the trade-offs alongside the wins. Everything we share follows those rules.
BackboardIO
@BackboardIO
10h
Backboard delivered up to 12.8× better p90 interactivity in AgentX than SGLang. In @SemiAnalysis_' agentic inference benchmark, Backboard running at BF16 (full precision) achieved not just that superior interactivity but 13.6× faster time to first token. and 1.3× higher total
Qwen3.8-Flash-Next: 12.8× Interactivity vs SGLang | Backboard
From backboard.io
1
BackboardIO
@BackboardIO
Nov 7
More useful work from the same GPUs. Using Qwen3.8-Flash-Next on eight H100 GPUs. Backboard managed up to 2.2× higher output throughput per GPU than the SGLang results on SemiAnalysis AgentX. This was done at BF16 versus SGLang at FP8. Better throughput without sacrificing model precision.

BackboardIO’s posts