]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: support for weight clamp in top-k norm (llama/16702)
authorAman Gupta <redacted>
Mon, 27 Oct 2025 01:06:16 +0000 (09:06 +0800)
committerGeorgi Gerganov <redacted>
Sun, 9 Nov 2025 21:38:03 +0000 (23:38 +0200)
commit97c3285cc4d09c0f0b5450c891bac4835d452053
tree155e4d3779956d952e34ba75ff7e6e493bd313d6
parentbd8734c05064524ab6da89785e2c9c8d5c29f2e6
CUDA: support for weight clamp in top-k norm (llama/16702)
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/topk-moe.cu
ggml/src/ggml-cuda/topk-moe.cuh