llama.cpp/tests/test-backend-ops.cpp at c9e7cbb08b70b73729f5e73ec27064ccb51b271c

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00

Files

Jeff Bolz bd38ddea01 vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11166 )

* vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl

Shaders are based on cpy.cu.

* vulkan: support copy from q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl to f32

* ggml: copy q->f32 assumes some contiguity in the destination

2025-01-16 22:47:10 +01:00

158 KiB

Raw Blame History

View Raw

158 KiB Raw Blame History

158 KiB

Raw Blame History