GitHub - deepseek-ai/DeepInfer: DeepInfer: High-performance, large-scale inference framework for DeepSeek models

DeepInfer is the high-performance inference framework that powers DeepSeek's large-scale production services. This open-source release provides offline inference with the core features needed for serving at scale. Supported models: DeepSeek-V4.1-Flash Supported features: Optimized kernels, model and sampler runtime Parallelism: Attention DP / balanced CP, MoE EP + EPLB DSpark and confidence-schedu

[rgfx]

Supported hardware:にHuawei Ascend 950 NPUsがあるのが流石。CUDAの代替技術でCANNってのをやってるのか。

[shinobue679fbea]

オレオレ推論エンジンが流行ってるが、公式が出してくれるとパクリ甲斐があるな