[Bug]:amd mi308x gpu, vllm 0.27.0~0.27.1, rocm 7.2.3, Kimi-K2.7-Coder start fails:AssertionError: mla_gluon requires gfx950 (CDNA4), got gfx
![[Bug]:amd mi308x gpu, vllm 0.27.0~0.27.1, rocm 7.2.3, Kimi-K2.7-Coder start fails:AssertionError: mla_gluon requires gfx950 (CDNA4), got gfx](https://www.chat-gpts.plus/wp-content/uploads/2026/08/51964-339b289b-768x403.jpg)
该报错通常发生在使用 AMD MI308X(gfx942)等非 gfx950 架构 GPU 加载 Kimi-K2.7-Coder 等模型时,vLLM 0.27.0~0.27.1 的 ROCm 版本因模型代码中 mla_gluon 算子的架构检查失败而启动中止。优先排查方向是升级 vLLM 到最新 m


![[Question]: Getting all 0 vector similarity in retrieval testing by adding a reranker model](https://www.chat-gpts.plus/wp-content/uploads/2026/08/9388-f8d94761-768x403.jpg)





