]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: add softmax broadcast (llama/14475)
authorAman Gupta <redacted>
Wed, 2 Jul 2025 12:34:24 +0000 (20:34 +0800)
committerGeorgi Gerganov <redacted>
Sat, 12 Jul 2025 16:23:56 +0000 (19:23 +0300)
commitfb5c4095ee439be18c3ba02a3919b12f775578cd
tree1d2045ab7e828449453b36e47bc48c029d309912
parent70515ed728976d2eb64936417359ded81eaab2bc
CUDA: add softmax broadcast (llama/14475)

* CUDA: add softmax broadcast

* Pass by const ref

* Review: Use blockDims for indexing, remove designated initializers

* Add TODO for noncontigous input/output
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/softmax.cu