DeepSeek's open stack behind V4.1 Flash: weights, kernels, DeepInfer, 3FS
A rundown of what DeepSeek has opened around V4.1 Flash: MIT weights, FlashMLA, DeepEP, DeepGEMM, 3FS, DeepInfer and the deployment recipe, with only training data kept closed.
A reminder of what the whale 🐋 has made open: > weights, under MIT > FlashMLA, attention kernels at 580 TFLOPS on H800 > DeepEP, the communication library for MoE > DeepGEMM, FP8 matrix multiply at 1,350+ TFLOPS. > 3FS, an entire distributed file system they built for themselves. > DeepInfer, the in house inference framework and the engine behind V4.1 Flash > deepseek-recipe so your deployment behaves like their API so you can also gain insane margin This is freakin every layer of an AI lab. Model, kernels, communication, storage, serving. Except their training data - there is nothing else really they haven’t made it open to the world. 🌎 I can’t love and thank them enough. 💙🐳