]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
opencl: add basic support for q5_0 and q5_1 (llama/23548)
authorshaofeiqi <redacted>
Mon, 1 Jun 2026 17:06:50 +0000 (10:06 -0700)
committerGeorgi Gerganov <redacted>
Mon, 8 Jun 2026 11:36:36 +0000 (14:36 +0300)
commite728bae15950e1786b4c9574fa56a889e772f516
tree79a60503dfdf1ae16cfa4187cb25057676f676b8
parent050b8567a0fff75392c249d9283f8ee2dfa89292
opencl: add basic support for q5_0 and q5_1 (llama/23548)

* opencl: add general q5_0 support

* opencl: add general q5_1 support

* opencl: support non-uniform workgrp size

---------

Co-authored-by: Li He <redacted>
ggml/src/ggml-opencl/CMakeLists.txt
ggml/src/ggml-opencl/ggml-opencl.cpp
ggml/src/ggml-opencl/kernels/cvt.cl
ggml/src/ggml-opencl/kernels/mul_mm_q5_0_f32_l4_lm.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/mul_mm_q5_1_f32_l4_lm.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/mul_mv_q5_0_f32.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/mul_mv_q5_0_f32_flat.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/mul_mv_q5_1_f32.cl [new file with mode: 0644]
ggml/src/ggml-opencl/kernels/mul_mv_q5_1_f32_flat.cl [new file with mode: 0644]