Zhijian Liu
@zhijianliu
Building something new (@inco_ai).
Faculty @UCSanDiego (running
Prev: PhD @MIT. RS @NVIDIA.
Efficient AI. Views are my own.
1K Following 9.9K Followers
⚡️ Along with this version, we've also released our DFlash 2 drafter for Qwen3.8-Flash-Next!
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.
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
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
Congrats on the release! ⚡
DFlash 2 for GLM-5.3-Flash is cooking. Very soon!!
DFlash 2 is here! Qwen3.8-27B at 70 tok/s on an M5 Max MacBook Pro.
⚡ Up to 4.6× the speed of autoregressive decoding, with the same output.
This is the next generation of DFlash, seeded at Z Lab and upgraded at Inco AI. Get one more accepted token on every pass, for free!
Show more
