Xiang Guo

rfc: propose split op for oneDNN Graph API

16

This RFC is to add a new Split operation to oneDNN graph API opset. The rendered version: [link](https://github.com/xiang1guo/oneDNN/tree/xiang/rfcs/graph-split-op/rfcs/20230323-add-split-graph-op)

Hi, team When I am trying to use cliloader on windows, I met an error: `cliloader Error: loading DLL: The specified module could not be found.` The build option I...

### Background Preliminary work for MFDNN-13442. The main purpose of this PR is to bind the `fusion_info` as an attribute directly onto the op, rather than using a `fusion_info_key` to...

graph: backend: dnnl: fix decompose kernel select index check

2

Fix MFDNN-13765. Add check logic to fall back unsupported sdpa case to large_partition kernel. ``` ONEDNN_VERBOSE=1,filter=graph KMP_AFFINITY=compact,1,0,granularity=fine OMP_NUM_THREADS=4 OMP_PLACES=threads OMP_PROC_BIND=close numactl --membind= 0 --physcpubind=0-3 ./tests/benchdnn/benchdnn --graph --dt=7:f32+8:f32+9:f32+10:f32 --case=/home/sdp/xiangguo/onednn/oneDNN/mha-pt-starcoder-inf-bf16-bs1.json.json onednn_verbose,v1,info,oneDNN v3.9.0...

[Graph| tests, example, doc] Add GQA v2 support for implicit causal mask and example, doc update

2

Follow-up work based on #2931 - [x] GQA v2 implicit causal mask test cases support - [x] Add example for GQA v2 pattern. - [x] Doc update.

graph: backend: dnnl: backend refactor and sdpa v1 kernel support quantize SDPA

1

### Background This is a follow-up work based on #2930 and #2931. The PR mainly focuses on supporting quantized SDPA with internal dnnl_sdpa. It helps to reduce graph compilation time...

AArch64: graph fusion and graph ci cases failed in AArch64 platform

6

This is created to track graph-related failure cases in AArch64 platform. Currently, they are skipped in CI testing [script](https://github.com/uxlfoundation/oneDNN/blob/70519642176a6d8f5761f657ea6b82e03bbb9120/.github/automation/aarch64/skipped-tests.sh#L31-#L35).