Charro Gruver
Charro Gruver
/approve
@ochafik Fantastic work here. Do you have an ETA for getting this PR ready to merge? I'm experimenting with the Continue.dev VSCode extension in OpenShift Dev Spaces (Eclipse Che), and...
@ochafik @ericcurtin PTAL - https://github.com/ochafik/llama.cpp/pull/3
For those who are following this PR, I am trying to maintain a merge from this branch and the master branch of llama.cpp here - https://github.com/cgruver/llama.cpp/tree/tools
@akurinnoy understood. I still believe that it would be nice to be able to declare a workspace name rather than have one auto-generated. I've observed a lot of users struggle...
https://issues.redhat.com/browse/CRW-9437
@ibuziuk Let me take a look at that. I would still like to consider configurable defaults. Plus, it feels like an anti-pattern that we set limit and requests to be...
@NeoZhangJianyu Results on the Intel Arch - ``` llama-run --ngl 999 llama-2-7b.Q4_0.gguf hello Loading modelget_memory_info: [warning] ext_intel_free_memory is not supported (export/set ZES_ENABLE_SYSMAN=1 to support), use total memory as free memory...
> Yes, I see same result in Ubuntu on Arc 770. It should be OK. > > It's decided by the quantized model, instead of llama.cpp code. You could check...