[Bug]: cuda_archs_loose_intersection drops plain “10.0” when TORCH_CUDA_ARCH_LIST also has “10.0a”, producing sm_100a-only kernels that fail
![[Bug]: cuda_archs_loose_intersection drops plain "10.0" when TORCH_CUDA_ARCH_LIST also has "10.0a", producing sm_100a-only kernels that fail](https://www.chat-gpts.plus/wp-content/uploads/2026/10/56548-3c41a23b-768x403.jpg)
报错为 no kernel image is available for execution on the device ,通常发生在本机编译 vLLM 时: TORCH_CUDA_ARCH_LIST 同时包含 10.0 和 10.0a , cuda_archs_loose_intersection
![[Bug]: The Deepseek v4 model compiles kenrel during the inference process](https://www.chat-gpts.plus/wp-content/uploads/2026/10/48809-e96fa9bb-768x403.jpg)
![issue: Realtime call: spoken replies reach the chat model as assistant messages starting with "[Historical voice assistant transcript…]", an](https://www.chat-gpts.plus/wp-content/uploads/2026/10/32664-bd45fb08-768x403.jpg)

![[Roadmap] vLLM Roadmap Q3 2026](https://www.chat-gpts.plus/wp-content/uploads/2026/10/48168-07ca8ed3-768x403.jpg)




