Inco AI
@inco_ai
Inference, reimagined for the agentic era
21 Following 3.9K Followers
Had a lot of fun talking at @modal Runtime yesterday! We released DFlash nine months ago, and now NVIDIA, AMD, Google and Meta are building on it.
Kick off #SFTechWeek# with Inco AI + TokenRouter at our Token Happy Hour! 🍸
📅 Oct 5, 4:30–7pm
📍 Industrious, Palo Alto
Come talk AI over batched cocktails + bites.
RSVP:
Show more
Really enjoyed working with @linewiseAI on this!
16,190 hours of video a week is 8 years of watching for one person. Their agent gets through it in about a day, and it runs on Inco.
Proud of the team on both sides.
Show more
We have been spending tons of efforts into optimizing our inference stack across all layers - and one of the reason we do this is to enable companies like @linewiseAI run their applications at scale 🚀
Drop me a note if you want to work with us!
Show more
31× more video per GPU, at 1/15 the cost ⚡
That's @linewiseAI's video agent on Inco vs. their own pipeline.
The agent is thorough. Before it calls a moment idle, it checks what came before and after, reads the sensors, and zooms in. Lots of model calls, and we make them fast.
Show more
One week of our video data: 16,190 hours. A full-time worker would need 8 years to watch it.
Our agent-native infra analyzes it in a day, with inference on @inco_ai: 31× the throughput per GPU at 1/15 the cost per hour of video.
Show more
DFlash drafts a whole block in parallel. DFlash 2 picks one path through the block instead of the top token at each position: over 20% more tokens per pass, about 1% more latency.
Our co-founder and chief scientist @zhijianliu explains how at @modal Runtime in SF on Oct 1.
Show more
DFlash drafts a whole block in parallel. DFlash 2 picks one path through the block instead of the top token at each position: over 20% more tokens per pass, about 1% more latency.
Our co-founder and chief scientist @zhijianliu explains how at @modal Runtime in SF on Oct 1.
Show more
Qwen3.8-27B, up to 144 tok/sec on M5 Max.
Let that sink in. ⚡️✨🚀
Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0!
Get it running now:
Show more
Splash is here! A month ago, DFlash 2 ran Qwen3.8-27B at 70 tok/s on an M5 Max. Today, Splash runs it at 144 tok/s on the same Mac ⚡
Getting that speed used to take work. Splash is built around the model, with the DFlash 2 draft already in it. Two commands and you're running.
Show more
Qwen3.8-27B at 144 tok/s on an M5 Max MacBook Pro ⚡
Meet Inco Splash: our open-source inference engine, built around the model and around Apple silicon.
Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents.
Show more
⚡ 532 tokens/s!
DeepSeek V4.1 Flash is live on Inco, and it's the fastest provider on Artificial Analysis. #1# output speed. Not close.
Try it:
Results:
Show more
