hydai
hydai
Is this model supported by llama.cpp?
Could you please try llama.cpp with CUDA enabled to run this model? Since this is an internal error in the llama.cpp CUDA backend, I would like to know if this...
Hi @hiroshi Thanks for this issue. The WasmEdge-go is not yet up-to-date with 0.14.0. If you are interested in using Go SDK, you can try to downgrade to 0.13 or...
Closing this because we already support Gemma3-Vision, which is sufficient to replace Llama-3.2-Vision.
> note: for manylinux_2_28_x86_64 , use `add_definitions(-D_GLIBCXX_USE_CXX11_ABI=0)` and install pytorch with no c++11 abi will work I see, so there is still a compatible issue about the C++11 ABI in...
Looks fine. I expect there will be more details for M3 to M5 after you finish the survey during M2.
> M1 is Done. Please convert your milestones into a checklist and mark some of them as done.
> @hydai A few more issues are left to replicate, so I would need a few days more on M2, I have updated the milestones accordingly. Sorry for the inconvenience...
> @hydai I have replicated 9 issues and documented their replication steps and remarks, and I'm working on a few more issues. Is there any medium via which I can...
Please go ahead and pick one of them and start to fix it.