frob

Failed in `ggml_compute_forward` which is deep inside llama.cpp. There are currently no open tickets in the [issue tracker](https://github.com/ggerganov/llama.cpp/issues), perhaps filing one will get a response from somebody who has seen...

[Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging.

``` Jun 15 08:10:25 ml-ai-ubuntu-gpu-mi300x1-192gb-atl1 ollama[5704]: time=2025-06-15T08:10:25.798Z level=INFO source=server.go:168 msg=offload library=rocm layers.requested=-1 layers.model=62 layers.offload=62 layers.split="" memory.available="[191.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="167.8 GiB" memory.required.partial="167.8 GiB" memory.required.kv="16.2 GiB" memory.required.allocations="[167.8 GiB]" memory.weights.total="150.0 GiB" memory.weights.repeating="149.3...

```console $ mkdir 0.12.10 && cd 0.12.10 && git clone https://github.com/ollama/ollama -b v0.12.10 . && cmake -B build Cloning into '.'... remote: Enumerating objects: 41175, done. remote: Counting objects: 100%...

Needs hybrid support in llama.cpp: https://github.com/ggerganov/llama.cpp/pull/7531

The initial release of the llama3.1 models didn't have a template that supported tools, if you re-pull it you should get the update.

Not yet, there is an open ticket: https://github.com/ollama/ollama/issues/5794

``` time=2025-10-30T15:45:32.702+08:00 level=WARN source=sched.go:397 msg="model architecture does not currently support parallel requests" architecture=qwen3vl ``` https://github.com/ollama/ollama/blob/0a2d92081bb6b6b2d3eab5908fce08cfcf736e1d/server/sched.go#L393-L398

The log is truncated on the right, use this instead: `journalctl -u ollama --no-pager`.

``` Apr 28 17:20:32 GZ302EA ollama[2328]: time=2025-04-28T17:20:32.869+08:00 level=INFO source=server.go:138 msg=offload library=rocm layers.requested=-1 layers.model=33 layers.offload=17 layers.split="" memory.available="[3.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.9 GiB" memory.required.partial="3.4 GiB" memory.required.kv="256.0 MiB" memory.required.allocations="[3.4 GiB]" memory.weights.total="4.3 GiB" memory.weights.repeating="3.9...