]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
metal : copy kernels for quant to F32/F16 conversions (llama/12017)
authorGian-Carlo Pascutto <redacted>
Tue, 25 Feb 2025 09:27:58 +0000 (10:27 +0100)
committerGeorgi Gerganov <redacted>
Tue, 25 Feb 2025 11:33:09 +0000 (13:33 +0200)
commit314cd17d2917384bd6abadc6e46758ef1c038b24
tree9f6ff4c10960be454846441913f1161e3b0b1f81
parentdd26b0f9eba9aafdc504fede5c2c2d8c8bc59fbb
metal : copy kernels for quant to F32/F16 conversions (llama/12017)

metal: use dequantize_q templates

---------

Co-authored-by: Georgi Gerganov <redacted>
src/ggml-metal/ggml-metal.m
src/ggml-metal/ggml-metal.metal