]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml-cuda: add mem check for fusion (llama/19916)
authorAman Gupta <redacted>
Fri, 6 Mar 2026 16:05:43 +0000 (00:05 +0800)
committerGeorgi Gerganov <redacted>
Sun, 15 Mar 2026 19:50:13 +0000 (21:50 +0200)
commit585070a81ad74d47f0841958406fa41d9487fecb
tree7bd0593bace25bc6b88d07b1586bc139db01064b
parentcbbcf7bfd15b7d34c77900528e6c832fdebed7da
ggml-cuda: add mem check for fusion (llama/19916)

* ggml-cuda: add mem check for fusion

* Replace NaNs with -FLT_MAX

* fix typo

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
src/ggml-cuda/ggml-cuda.cu
src/ggml-cuda/topk-moe.cu