Does DeepSeek provide the inference code along with the weights? I read here recently that for models where only the weights are released, providers have to implement which could be different than what the labs themselves use.
https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/...
> providers have to implement which could be different than what the labs themselves use.
I'd imagine (most) providers just take implementation by vLLM/SGLang.