Mr.Userbox comments

Results 45 comments of


                                            Mr.Userbox

ZLUDA for llama.cpp

i just found the repo few days ago and i havent try it yet but im very exited to give me time to test it out. I also have AMD...

ZLUDA for llama.cpp

We should make a discord group for ZLUDA and llamacpp

ZLUDA for llama.cpp

sup guys, some buddy already could run llamacpp with zluda? can share the steps please i would like to test it

ZLUDA for llama.cpp

one of the contributors of RocBLAS told me to try this into docker container. He claim that it make avaible to use all AMD gpus in your pc, old ones,...

Take my money

this project is open source, we have the code, we can code and find us time to improve and keep developing if we really interested. @Baigle if you want to...

Tensile won't produce backend libraries for archs without optimized logic files when using --separate-architectures

hello guys, fist of all thanks for all the hard work you doing to make rx5700 work, im just a hobbist and not even close to be near your league...

Tensile won't produce backend libraries for archs without optimized logic files when using --separate-architectures

@smirgol one of the contributors of rocblas says that we can compile llamacpp with hipblas and mix old and new gpus https://github.com/ROCm/rocBLAS/pull/1251#issuecomment-1936685074

Tensile won't produce backend libraries for archs without optimized logic files when using --separate-architectures

lol i just notice its cgmb, sup bro i just dm you in the other repo chat lol

AMD support

@danielhanchen does this will help bro? https://github.com/ROCm/triton/tree/triton-mlir what would be the next step?

Rocm6 not working with PCIE x1 gen1

@jamesxu2 sorry for the delay, i just saw the response. I have turn off my hobby computer that i use for testing AI stuff, going to turn it on this...