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	Jeff Bolz <redacted>
	Fri, 17 Jul 2026 06:42:59 +0000 (07:42 +0100)
committer	GitHub <redacted>
	Fri, 17 Jul 2026 06:42:59 +0000 (08:42 +0200)
commit	788e07dc91d266ad3162a1ce9037665656269689
tree	e37a1764d53553379bb39bb52c25c00ce21ced08	tree
parent	0bd0ec60998d0f71ec45471b633bf2403ac81956	commit \| diff

vulkan: Support Q2_0 (#25430)

* vulkan: Support Q2_0

The backend perf tests for mat-vec-mul weren't very good at first (worse than
q2_k), doubling the rows per workgroup made a big difference.

* reorder

* resolve merge conflict, adjust err threshold for f16->q2_0 set_rows

13 files changed:

ggml/src/ggml-vulkan/ggml-vulkan.cpp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/copy_to_quant.comp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/dequant_q2_0.comp	[new file with mode: 0644]	blob
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq.comp		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq_funcs.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_funcs.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_funcs.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_shmem_types.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/types.glsl		diff \| blob \| history
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history

Packaging of ggml-org/llama.cpp

RSS Atom