Skip to content

refactor: Turn GPUModelRunner.inputs_embeds to a CpuGpuBuffer#24345

Merged
vllm-bot merged 1 commit intovllm-project:mainfrom
protopia-ai:input-embeds-buffer
Sep 6, 2025
Merged

refactor: Turn GPUModelRunner.inputs_embeds to a CpuGpuBuffer#24345
vllm-bot merged 1 commit intovllm-project:mainfrom
protopia-ai:input-embeds-buffer

Commits

Commits on Sep 5, 2025