ddpasa

> I didn't intentionally fix this yet, but maybe I found and fixed some related issue in the meantime. Let me know when you have more details. Just ran more...

A related question: for embedded video cards, what limit for the memory should I use for vulkan? Is this something vulkaninfo can tell me? For example, running with 3GB of...

> For the record, it seems the bug in [ggerganov/llama.cpp#5545](https://github.com/ggerganov/llama.cpp/issues/5545) is now fixed. Yes, the Vulkan backend of llama.cpp is much more stable and mature now. I have been using...

There will soon be a vulkan backend to ollama. I'm nor sure if openvino is still needed when that starts working.

Hello @tyrasd , this is somewhat of an confusing topic. As far as I can see, the tag "name" has been hijacked because a lot of mappers are not really...

> It works now! I just forgot to add the `-fsycl` compiler flag. I also made it so you don't need to setup the oneAPI environment variables yourself, at build-time...

A related question is, do you know how the performance compares to Vulkan? Maybe you can also take a look here: https://github.com/ollama/ollama/issues/2396

> These are the oneAPI libraries we would need to bundle with ollama: > Library Size > libOpenCL.so 0.06M > libmkl_core.so 68M > libmkl_sycl_blas.so 97M > libmkl_intel_ilp64.so 20M > libmkl_tbb_thread.so...

> > Would this bundle something that would work on my laptop without needing to install oneapi? If so, I'm eager to try this out > > @ddpasa Yes, but...

take a look at: https://github.com/ollama/ollama/pull/2578