[Vvector]

Chip speed isn't as important as good software

[moralestapia]

The software is the same, AMD is not doing its own LLMs.

[jjice]

I think the software they were referring to is CUDA and the developer experience around the nvidia stack.

[moralestapia]

???

Know any LLMs that are implemented in CUDA?

[imtringued]

The average consumer uses llama.cpp. So here is your list of kernels: https://github.com/ggml-org/llama.cpp/tree/master/ggml/src/g...

And here is pretty damning evidence that you're full of shit: https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/g...

The ggml-hip backend references the ggml-cuda kernels. The "software is the same" (as in, it is CUDA) and yet AMD is still behind.

[moralestapia]

@tomhow personal attack

[wmf]

Ultimately all of them except Gemini.

[moralestapia]

Wrong.

Show me one single CUDA kernel on Llama's source code.

(and that's a really easy one, if one knows a bit about it)

[rnrn]

removing comment since I regret attempting to engage in this thread