AI 导读
AMD 在 vLLM 上游率先落地 MegaKernel 解码支持，早于 NVIDIA，这是 vLLM 重大功能首次仅支持 ROCm 而不支持 CUDA。MegaKernel 通过将内核启动次数减少 10 倍，对高交互性解码至关重要。CUDA 版 vLLM 目前连上游 MegaKernel 支持的草稿 PR 都还没有。
正文
ALERT🚨: AMD JUST LANDED SUPPORT FOR MEGAKERNEL DECODE IN UPSTREAM VLLM WELL BEFORE NVIDIA. This marks one of the first times that a major vLLM feature is only supported on ROCm and not on CUDA yet.
MegaKernels is a technique that is massively important for high-interactivity decoding by reducing the # of kernel launches by 10x.
This marks an❗️important milestone❗️for ROCm vLLM to land major ROCm-exclusive features. CUDA vLLM doesn't even have draft PRs for upstream vLLM megakernel support yet.
来源：SemiAnalysis · x.com