]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: only support F32/F16 for GGML_OP_REPEAT (#24533)
authorleonardHONG <redacted>
Mon, 15 Jun 2026 06:11:00 +0000 (14:11 +0800)
committerGitHub <redacted>
Mon, 15 Jun 2026 06:11:00 +0000 (09:11 +0300)
commit3686e9d6433fb286afd4508d8f8af920d194932e
tree1c5c35a67cda4f6aae3d6d634fef1d54c5c1f0fe
parent6e9007ae61f4e994c27484759caac6ef2aa32b30
CUDA: only support F32/F16 for GGML_OP_REPEAT (#24533)
ggml/src/ggml-cuda/ggml-cuda.cu
tests/test-backend-ops.cpp