]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 2bf3fbf)
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038)
authorGeorgi Gerganov <redacted>
Sat, 2 Aug 2025 14:13:05 +0000 (17:13 +0300)
committerGitHub <redacted>
Sat, 2 Aug 2025 14:13:05 +0000 (17:13 +0300)
commit15e92fd33791e60a4ddb5970b47242a855c27117
tree93c8cc06a52a6ba69a5d8181a0bddf1df0588b0etree
parent2bf3fbf0b54f97aef2b388b76d222789e1c170f1commit | diff
cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038)

* cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1

ggml-ci

* cont : fix cont types

ggml-ci

* cont : adopt variable names and comment from the other branch
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
ggml/src/ggml-sycl/ggml-sycl.cpp diff | blob | history
Packaging of ggml-org/llama.cpp