Igor Safonov

rfc: quantization: extending scaling support

12

# Description A link to the rendered document: [Link](https://github.com/igorsafo/oneDNN/tree/rfcs/rfcs/20220201-quantization-scaling)

# Description Here is the [link](https://github.com/igorsafo/oneDNN/tree/rfcs-gpt-quantization/rfcs/20231108-gpt-quantization)

rfcs: multi-head attention

5

# Description A link to the rendered document: [link](https://github.com/igorsafo/oneDNN/tree/igorsafo/rfcs/mha-optimization/rfcs/20231026-attention-optimization) Fixes # (github issue) # Checklist ## General - [ ] Do all unit and benchdnn tests (`make test` and `make...

# Description A link to the document: [link](https://github.com/igorsafo/oneDNN/tree/igorsafo/rfcs/indirect-kv-cache/rfcs/20240425-mha-indirect-kv) ## [RFC](https://github.com/oneapi-src/oneDNN/tree/rfcs) PR - [x] Does RFC document follow the [template](https://github.com/oneapi-src/oneDNN/blob/rfcs/rfcs/template.md#onednn-design-document-rfc)? - [x] Have you added a link to the rendered document?

# Summary oneDNN validation for Nvidia backend hits a correctness issue under benchdnn on int8 convolution (dst is s8) problems with sum post op. # Build ``` mkdir -p build...