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	lhez <redacted>
	Fri, 5 Jun 2026 20:45:25 +0000 (13:45 -0700)
committer	GitHub <redacted>
	Fri, 5 Jun 2026 20:45:25 +0000 (13:45 -0700)
commit	308f61c31f083251ce8150f10b9ef97679b500b5
tree	9c9ea110f2cdc3a4d88dd60fbcc5788108e08714	tree
parent	da87e9b612592ccd2a2e783eff631346459b9de0	commit \| diff

opencl: improve get_rows, cpy, concat and q6_k flat gemv (#24160)

* opencl: allow multiple workgroups for large rows

* opencl: improve small cpy

* opencl: packed concat for small input

* opencl: tweak flat q6_K gemv, increase N_DST and remap threads

Packaging of ggml-org/llama.cpp

RSS Atom

ggml/src/ggml-opencl/ggml-opencl.cpp		diff \| blob \| history
ggml/src/ggml-opencl/kernels/concat.cl		diff \| blob \| history
ggml/src/ggml-opencl/kernels/cpy.cl		diff \| blob \| history
ggml/src/ggml-opencl/kernels/get_rows.cl		diff \| blob \| history
ggml/src/ggml-opencl/kernels/mul_mv_q6_k_f32_flat.cl		diff \| blob \| history