精选理由
vLLM和Hugging Face搞了个大活：Transformers v0.25.0直接兼容vLLM，450多个模型自动加速，不用自己写适配代码了，开箱即用！
vLLM与Hugging Face团队在v0.25.0中实现了Transformers建模后端与手写vLLM模型的对等性能。现在450多种Transformers架构可以直接在vLLM中以原生速度运行，完全无需移植代码。用户只需集成一次Transformers即可自动获得vLLM的融合内核、torch.compile和CUDA图优化。这一更新大幅降低了在vLLM上使用新模型的工程成本。
原文 · vLLM
Big news from @hmellor_ + @huggingface team🙌! I…
Big news from @hmellor_ + @huggingface team🙌!
In v0.25.0 the Transformers modeling backend hits parity with hand-written vLLM models.
Now 450+ transformers architectures run in vLLM at native speed with zero porting. Integrate once with transformers to get vLLM's fused kernels, torch.compile, and CUDA graphs for free.
Read about the changes below 👇