]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (llama/11166)
authorJeff Bolz <redacted>
Thu, 16 Jan 2025 21:47:10 +0000 (15:47 -0600)
committerGeorgi Gerganov <redacted>
Mon, 3 Feb 2025 20:00:57 +0000 (22:00 +0200)
commit7183a1eb72bb4415e3b98a83884ac5d69f9eb6bc
tree53508ac5abe28bf2f73db1d48f08582f34fe9ac2
parent09f3c6664870dad525448e8da43e92d8c8f6fd20
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (llama/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
ggml/src/ggml-cpu/ggml-cpu.c
ggml/src/ggml-vulkan/ggml-vulkan.cpp
ggml/src/ggml-vulkan/vulkan-shaders/copy_from_quant.comp [new file with mode: 0644]
ggml/src/ggml-vulkan/vulkan-shaders/copy_to_quant.comp [new file with mode: 0644]
ggml/src/ggml-vulkan/vulkan-shaders/generic_unary_head.comp
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp