Zhijian Liu's banner

Zhijian Liu

@zhijianliu • 9,948 subscribers

Building something new (@inco_ai). Faculty @UCSanDiego (running https://t.co/dxXyoN9zSi). Prev: PhD @MIT. RS @NVIDIA. Efficient AI. Views are my own.

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

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!

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!

1,209,392 Aufrufe • vor 2 Monaten

Splash 1.3.0 is out! At launch we focused on decode speed. This time we worked on the wait before the first token. Watch the part where we come back to a project. With SSD offloading on, the first token takes about a second instead of 19.

Splash 1.3.0 is out! At launch we focused on decode speed. This time we worked on the wait before the first token. Watch the part where we come back to a project. With SSD offloading on, the first token takes about a second instead of 19.

68,190 Aufrufe • vor 26 Tagen

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.

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.

95,465 Aufrufe • vor 1 Monat

Reasoning VLAs can think. They just can't think fast. Until now. Introducing FlashDrive⚡ 🚀 716 ms → 159 ms on RTX PRO 6000 (up to 5.7×) ✅ Zero accuracy loss FlashDrive = streaming inference + DFlash speculative reasoning + ParoQuant W4A8 Real-time reasoning for autonomous driving is here!

Reasoning VLAs can think. They just can't think fast. Until now. Introducing FlashDrive⚡ 🚀 716 ms → 159 ms on RTX PRO 6000 (up to 5.7×) ✅ Zero accuracy loss FlashDrive = streaming inference + DFlash speculative reasoning + ParoQuant W4A8 Real-time reasoning for autonomous driving is here!

192,108 Aufrufe • vor 6 Monaten

Keine weiteren Inhalte verfügbar