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	Gaurav Garg <redacted>
	Wed, 10 Jun 2026 17:51:16 +0000 (23:21 +0530)
committer	GitHub <redacted>
	Wed, 10 Jun 2026 17:51:16 +0000 (23:21 +0530)
commit	e95dae18d64ae4471d61a9dc87880a64e0e5c86e
tree	279e047efb6ac390b17753fe1048633ade0d6347	tree
parent	d2462f8f7ac6d80070a587ffebf6cd73730f4280	commit \| diff

Remove padding and multiple D2D copies for MTP (#24086)

* Make ggml_gated_delta_net take only the initial recurrent state (D, 1, n_seqs) and passes the snapshot count K as an op parameter instead of inferring it from state->ne[1].

Remove the padding hack and copy all emitted snapshots into the recurrent cache with a single strided ggml_cpy

* Make GDN changes in all backends. Address review comments.

* Fix CI build errors

20 files changed:

ggml/include/ggml.h		diff \| blob \| history
ggml/src/ggml-backend-meta.cpp		diff \| blob \| history
ggml/src/ggml-cpu/ggml-cpu.c		diff \| blob \| history
ggml/src/ggml-cpu/ops.cpp		diff \| blob \| history
ggml/src/ggml-cuda/gated_delta_net.cu		diff \| blob \| history
ggml/src/ggml-hexagon/ggml-hexagon.cpp		diff \| blob \| history
ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c		diff \| blob \| history
ggml/src/ggml-metal/ggml-metal-device.cpp		diff \| blob \| history
ggml/src/ggml-metal/ggml-metal.metal		diff \| blob \| history
ggml/src/ggml-opencl/ggml-opencl.cpp		diff \| blob \| history
ggml/src/ggml-opencl/kernels/gated_delta_net.cl		diff \| blob \| history
ggml/src/ggml-sycl/gated_delta_net.cpp		diff \| blob \| history
ggml/src/ggml-vulkan/ggml-vulkan.cpp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/gated_delta_net.comp		diff \| blob \| history
ggml/src/ggml-webgpu/ggml-webgpu.cpp		diff \| blob \| history
ggml/src/ggml-webgpu/wgsl-shaders/gated_delta_net.wgsl		diff \| blob \| history
ggml/src/ggml.c		diff \| blob \| history
src/models/delta-net-base.cpp		diff \| blob \| history
src/models/models.h		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history

Packaging of ggml-org/llama.cpp

RSS Atom