]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix non-cont. inputs for batched mat mul (#13155)
authorJohannes Gäßler <redacted>
Tue, 29 Apr 2025 14:00:27 +0000 (16:00 +0200)
committerGitHub <redacted>
Tue, 29 Apr 2025 14:00:27 +0000 (16:00 +0200)
commitcdf76586b23c67abd3ca064ee2c084c57ae240bd
tree88d8f9e5778402ceecf98c197097777ec8e05e45
parent7d3af70b089bb349b5d17eb01839224c99ec1952
CUDA: fix non-cont. inputs for batched mat mul (#13155)
ggml/src/ggml-cuda/convert.cu
ggml/src/ggml-cuda/convert.cuh
ggml/src/ggml-cuda/ggml-cuda.cu
src/llama-model.cpp