]> git.djapps.eu Git - pkg/ggml/sources/ggml/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 10:02:19 +0000 (13:02 +0300)
commitac47d234ec637ba9ccebce8cb9243e28198f0992
tree6442e5f7d22eb28ae25da01d2db71b1fac0f277c
parentab0131eedee09462df15fd65cbe4f380e1fb0bfa
CUDA: fix crash on large batch size for MoE models (llama/13384)
src/ggml-cuda/getrows.cu