Alex

@Phylante Could you please share gdt file for ddraw?

Hi all! I've completely missed that Issues were not enabled for my repo, but I've enabled them now, thanks for pointing it out! Looks like our work is closely related...

@KerfuffleV2 >What I linked is a separate project I see. I meant your work here in repo `llama-rs` :) Anyway, you may be interested in newly added `exp`, `max`, `1_minus_x`...

>Is there a reason to implement those elementwise operations all separately instead of adding a generic elementwise map operation? I guess it was simpler for me to just add new...

@KerfuffleV2 Do I understand [quantization algo](https://github.com/KerfuffleV2/smolrsrwkv/blob/076d14882be2ca471796c555d3c967d8e4d2585d/smolrwkv/src/quantized/model_impls.rs#L25) correctly, that for each matrix row, you determine min and max value, and then represent each element as `(uint8) ((e - min) / (max...

Hi all! Maintainer of [rwkv.cpp](https://github.com/saharNooby/rwkv.cpp) here. Indeed, having a separate repository for RWKV leads to `ggml` version lag, lack of computation backends that I can't commit to support with my...

>what would `llama.cpp` need in order to add support for a new arch that is more different compared to what we are used to Regarding `ggml`: for a long time...

Hi! The module `rwkv-cpp` in `llama-node` [explicitly points](https://github.com/Atome-FE/llama-node/tree/main/packages/rwkv-cpp/rwkv-sys) to a specific version of `rwkv.cpp`: [rwkv.cpp @ 363dfb1](https://github.com/saharNooby/rwkv.cpp/tree/363dfb1a061507aee661300fc8e2e153b6e99dc2). In turn, this version of `rwkv.cpp` explicitly points to a specific version of...

If it helps debugging, for some reason `llama.cpp` loads the RWKV file, not `rwkv.cpp`: ``` llama.cpp: loading model from /Users/andreas/rozek/AI/RWKV/RWKV-4-World-0.1B-v1-20230520-ctx4096.bin ```

Hi all! Looks like there is no ggml implementation of RWKV yet, and nobody have announced they would like to implement it. Today I've started trying to port RWKV to...