-
Notifications
You must be signed in to change notification settings - Fork 1k
Pull requests: oneapi-src/oneDNN
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
gpu: nvidia: ip: adjust benchdnn error threshold
component:tests
Codeowner: @oneapi-src/onednn-arch
documentation
A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
platform:gpu-nvidia
Codeowner: @oneapi-src/onednn-gpu-nvidia
#2479
opened Jan 22, 2025 by
sgeor255
Loading…
[rls-v3.6] xe: ocl: fix micro sdpa optional mask and tile_ops const correctness
backport
platform:gpu-intel
Codeowner: @oneapi-src/onednn-gpu-intel
#2438
opened Jan 17, 2025 by
xiang1guo
Loading…
test: benchdnn: inputs: matmul: add random ci test
component:tests
Codeowner: @oneapi-src/onednn-arch
documentation
A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
platform:gpu-intel
Codeowner: @oneapi-src/onednn-gpu-intel
#2434
opened Jan 17, 2025 by
rjoursler
Loading…
xe: ocl: sdpa: pull grouped scales out of gemm where possible
platform:gpu-intel
Codeowner: @oneapi-src/onednn-gpu-intel
#2409
opened Jan 15, 2025 by
petercad
Loading…
Fix accuracy of max-pooling backpropagation for bfloat16 data
component:tests
Codeowner: @oneapi-src/onednn-arch
platform:cpu-x64
Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
Fixed issue with installed multiple versions of the OpenCL which lead…
#2378
opened Jan 11, 2025 by
redradist
Loading…
[GPU] Improve reference kernel coverage.
component:tests
Codeowner: @oneapi-src/onednn-arch
platform:gpu-intel
Codeowner: @oneapi-src/onednn-gpu-intel
#2366
opened Jan 9, 2025 by
dyoussif
Loading…
xe: jit: gemm: remove mixing of oneDNN and gemmstone code
platform:gpu-intel
Codeowner: @oneapi-src/onednn-gpu-intel
#2363
opened Jan 9, 2025 by
rjoursler
Loading…
generic:sycl: Inner Product Backward
component:tests
Codeowner: @oneapi-src/onednn-arch
documentation
A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
platform:gpu-generic
Codeowner: @oneapi-src/onednn-gpu-generic
#2360
opened Jan 9, 2025 by
AD2605
Loading…
2 tasks done
[WIP] cpu: binary: add post-ops support for binary select op
component:api
Codeowner: @oneapi-src/onednn-arch
component:tests
Codeowner: @oneapi-src/onednn-arch
#2342
opened Jan 6, 2025 by
avmanerikar
•
Draft
x64: brdgmm conv: enable zps per group (backport)
backport
platform:cpu-x64
Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
generic: sycl: Introduce spec constants for sycl matmul
component:tests
Codeowner: @oneapi-src/onednn-arch
platform:gpu-generic
Codeowner: @oneapi-src/onednn-gpu-generic
#2250
opened Dec 11, 2024 by
ShanoToni
Loading…
rfcs: add a proposal on MatMul reduction API
RFC
A design document
#2152
opened Oct 4, 2024 by
densamoilov
Loading…
rfc: dnncompat compatibility layer
RFC
A design document
#2101
opened Sep 19, 2024 by
sgeor255
Loading…
rfcs: add proposal for collecting and analyzing synthetic data
RFC
A design document
#1999
opened Jul 18, 2024 by
rjoursler
Loading…
rfcs: add proposal for indirect KV cache support
RFC
A design document
#1894
opened May 3, 2024 by
igorsafo
Loading…
2 tasks done
ProTip!
Follow long discussions with comments:>50.