mirror of
https://github.com/ollama/ollama.git
synced 2025-09-09 20:42:59 +02:00
ea85e27bbd
* Enable CUDA Graphs for gemma3n. Similar to https://github.com/ggml-org/llama.cpp/pull/14741, though ollama has a slightly different model graph than llama.cpp which requires different workaround checks. * Remove residual check by reshaping differently in gemma3n model This should make the heuristics more robust