]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: fix crash on large batch size for MoE models (llama/13384)
authorJohannes Gäßler <redacted>
Fri, 9 May 2025 10:14:04 +0000 (12:14 +0200)
committerGeorgi Gerganov <redacted>
Tue, 13 May 2025 10:59:21 +0000 (13:59 +0300)
commit4b7cbb62efadcbc4667f1a5eecdd223d2e852fce
tree8a2019d048a447b08d4303b2c40b9919bf2d518f
parente27c91f6d63f7d94733a36ca212a66a50026d049
CUDA: fix crash on large batch size for MoE models (llama/13384)
ggml/src/ggml-cuda/getrows.cu