Meng, Hengyu
Meng, Hengyu
@ggerganov have you checked your gmail, there should be invitation email of intel developer cloud and related instructions, I think it will include SSH access
@ggerganov have you got the access to the machine?
@ggerganov do you need more support from us?
> @airMeng Don't think anything is needed from your side for now. I'm working with Intel Customer Support to resolve some connectivity issues. Feel free to reach over email for...
@ClarkChin08 please take a look
I am generating ```ze_module_handle_t``` directly via [nGen](https://github.com/oneapi-src/oneDNN/tree/master/src/gpu/jit/ngen)
seems our address might be wrong ``` There are no relocations in this file. The decoding of unwind sections for machine type Intel Graphics Technology is not currently supported. Symbol...
yes, I will split it into several PRs, the first PR will update the ```ggml_conv_2d``` as the above and keep the current im2col implementation in each backend itself, does it...
Okay it takes me a weekend to try it on the Metal backend and find it really a lot of changes. Can I only dispatch on the SYCL backend? It...
I think this is not expected since the latest LLM will introduce much longer and longer training context length