]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
CUDA: fix overflow in MMA kernel without stream-k (llama/17939)
authorJohannes Gäßler <redacted>
Fri, 12 Dec 2025 16:43:58 +0000 (17:43 +0100)
committerGeorgi Gerganov <redacted>
Sun, 14 Dec 2025 14:40:47 +0000 (16:40 +0200)
commit6c0e23651245b1c887b7072e0e8d03f61db9ab87
treec8b0cc61988b12ab31512ea7c032cce3fe72b4fc
parent83011bcf2564a7c5693d4d6f306fa7888524aada
CUDA: fix overflow in MMA kernel without stream-k (llama/17939)
src/ggml-cuda/fattn-common.cuh
src/ggml-cuda/fattn-mma-f16.cuh