mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-24 07:28:27 +00:00
When we later have a large batch running purely on a CPU, this results the error: GGML_ASSERT(talloc->buffer_id >= 0) Disabling this means that we will incrementally reallocate memory as the graph grows. Fixes #10410