vLLM CUDA构建迁移至稳定ABI
vLLM 表示，其 CUDA 构建现已采用 PyTorch 的 LibTorch Stable ABI，兼容的 LibTorch 更新无需重建或更新 vLLM 即可导入。自 v0.33.0 起，项目发布 LibTorch ABI Stable CUDA wheel，并在 CI 中使用 torch-abi-audit 检查不稳定符号。稳定 ABI 并不保证兼容所有 PyTorch 版本，Python API、GPU 与 CUDA 要求以及第三方依赖仍会影响兼容性。
此次迁移可让 vLLM 用户和软件包分发方在减少重建的情况下采用兼容的 PyTorch wheel，vLLM 后续还将把稳定 ABI 覆盖范围扩展至 CPU 和 ROCm 构建。
Introduction
vLLM relies heavily on PyTorch, with frequent calls to LibTorch in its C++ backend. As a result, changes to LibTorch’s binary interface may require vLLM to be rebuilt and relinked, even when the APIs remain unchanged. What if we could update LibTorch without rebuilding vLLM? That’s where the LibTorch Stable ABI comes in. With a LibTorch Stable ABI, updating LibTorch does not require rebuilding or updating vLLM in order to keep using it. Instead, we could swap out the torch wheel and import it directly into our vLLM package. As of v0.33.0, vLLM publishes LibTorch ABI Stable CUDA wheels.
