]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: fix bad asserts for partial offload (#13337)
authorJohannes Gäßler <redacted>
Tue, 6 May 2025 11:58:51 +0000 (13:58 +0200)
committerGitHub <redacted>
Tue, 6 May 2025 11:58:51 +0000 (13:58 +0200)
commit2356fb1d53c86d838756211010bbabfafda7cb94
tree300c80b2f8fb406f414ece9553b4f2d6ef3e6937
parent764b85627b46f43d7ea801867cd1b6abef484574
CUDA: fix bad asserts for partial offload (#13337)
ggml/include/ggml.h
ggml/src/ggml-cuda/fattn-common.cuh
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/mmq.cu
ggml/src/ggml-cuda/mmvq.cu
ggml/src/ggml.c