]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 80dd7ff)
sycl : Fixes to broken builds and test-backend-ops (#10257)
authorAlberto Cabrera Pérez <redacted>
Wed, 13 Nov 2024 09:40:57 +0000 (09:40 +0000)
committerGitHub <redacted>
Wed, 13 Nov 2024 09:40:57 +0000 (09:40 +0000)
commit2e82ffa4af29f87e7d3d6dff8060a2a79613b72f
tree5d78602b8a3523e26ceec71d78b775a36b6d8763tree
parent80dd7ff22fd050fed58b552cc8001aaf968b7ebfcommit | diff
sycl : Fixes to broken builds and test-backend-ops (#10257)

* Fixes broken build for the SYCL CUDA backend caused by non-explicit gemm call in outprod (merged in with RWKV6 in
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration #10133)

* Marks permuted MUL_MAT as unsupported to be able to run test-backend-ops

* Fixes asserts in norm to fix debug builds.
ggml/src/ggml-sycl.cpp diff | blob | history
ggml/src/ggml-sycl/norm.cpp diff | blob | history
ggml/src/ggml-sycl/outprod.cpp diff | blob | history
Packaging of ggml-org/llama.cpp