frob

> built Ollama with CUDA support on a SuSE system with CUDA 13.0. 12.8 > I don't think I can use 13.0 because it doesn't support my GPU. 13.0 supports...

Post the full [server log]( https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md).

Perhaps https://github.com/ggml-org/llama.cpp/issues/15049

Can you upload the PDF and give a pointer to the client that you are using?

I asked about the client so that I could replicate the problem as closely as possible, but it looks too time-consuming so I instead just tested ollama. Baseline: test with...

Your logs don't contain enough information, you removed the actual content that FastGPT is sending to ollama. If you add OLLAMA_DEBUG=1 to your server environment and try again, the resulting...

You need to set `OLLAMA_DEBUG=1` in the server environment. Run this command: ``` sudo systemctl edit ollama ``` Add these lines: ``` [Service] Environment="OLLAMA_DEBUG=1" ``` Save and exit, then run...

Your context size is too small for the size of the document you are attempting to summarize. For most of the tests, you used qwen2.5:32b with a context of 30001:...

You have `OLLAMA_NUM_PARALLEL` unset. In ollama-5.log, you set a context size of 96001. Since you have lots of VRAM, ollama first tries to load the model with `OLLAMA_NUM_PARALLEL=4`. That is,...

You can set `OLLAMA_SCHED_SPREAD=1` to have ollama divide the model across all cards. Theoretically this will allow each of the GPUs to work on a different completion at the same...