]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: support for weight clamp in top-k norm (#16702)
authorAman Gupta <redacted>
Mon, 27 Oct 2025 01:06:16 +0000 (09:06 +0800)
committerGitHub <redacted>
Mon, 27 Oct 2025 01:06:16 +0000 (09:06 +0800)
commit75d33b9302f84a5b89f82205d2bcd8def5a64e0a
tree76e71c7f8e99f4ec18235389841677f334014421
parent3470a5c891dcc94363e492a3760af92b6b07241c
CUDA: support for weight clamp in top-k norm (#16702)
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/topk-moe.cu
ggml/src/ggml-cuda/topk-moe.cuh
tests/test-backend-ops.cpp