git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit

overview / pkg / ggml / sources / llama.cpp / commit

author	Aman Gupta <redacted>
	Fri, 29 Aug 2025 03:35:58 +0000 (11:35 +0800)
committer	GitHub <redacted>
	Fri, 29 Aug 2025 03:35:58 +0000 (11:35 +0800)
commit	009b709d6efd24820ac67765ed339a72dc797814
tree	7f5f4e132634d71960c9729204e6c0e947170409	tree
parent	e8d99dd0b67f2ecc1e45fca8074a3a18c3e036d2	commit \| diff

CUDA: fuse adds, fuse add with rms norm (#15631)

* CUDA: fused add with rms_norm_mul

* Non-broadcast fuse works

* Add fused adds

* format

* Remove n_fuse from template params

* Address review comments

* Move template inside binbcast

Packaging of ggml-org/llama.cpp

RSS Atom

ggml/src/ggml-cuda/binbcast.cu		diff \| blob \| history
ggml/src/ggml-cuda/binbcast.cuh		diff \| blob \| history
ggml/src/ggml-cuda/ggml-cuda.cu		diff \| blob \| history
ggml/src/ggml-cuda/norm.cu		diff \| blob \| history
ggml/src/ggml-cuda/norm.cuh		diff \| blob \| history