]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (llama/16900)
authorRuben Ortlam <redacted>
Sat, 29 Nov 2025 08:37:22 +0000 (09:37 +0100)
committerGeorgi Gerganov <redacted>
Thu, 11 Dec 2025 13:32:49 +0000 (15:32 +0200)
commit879109af90c0aa567fdc9fb3e1c3ba2b04efbac0
tree8985e217f8a56e600fbadae35444d718db87356a
parentc12559bcdaebe08b3619e003cfd97dc3c013d733
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (llama/16900)

* vulkan: split mul_mmq_funcs for mul_mat_vecq use

* add mxfp4 mmvq

* add q2_k mmvq

* add q3_k mmvq

* add q4_k and q5_k mmvq

* add q6_k mmvq

* handle 4x4 quants per mmvq thread

* enable MUL_MAT_ID mmvq support

* enable subgroup optimizations for mul_mat_vec_id shaders

* device tuning

* request prealloc_y sync after quantization

* fix indentation

* fix llvmpipe test failures

* fix mul_mat_id mmvq condition

* fix unused variable warning
12 files changed:
src/ggml-vulkan/ggml-vulkan.cpp
src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl
src/ggml-vulkan/vulkan-shaders/generic_binary_head.glsl
src/ggml-vulkan/vulkan-shaders/generic_unary_head.glsl
src/ggml-vulkan/vulkan-shaders/mul_mat_vec.comp
src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.glsl
src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iface.glsl
src/ggml-vulkan/vulkan-shaders/mul_mat_vecq.comp
src/ggml-vulkan/vulkan-shaders/mul_mat_vecq_funcs.glsl [new file with mode: 0644]
src/ggml-vulkan/vulkan-shaders/mul_mmq.comp
src/ggml-vulkan/vulkan-shaders/mul_mmq_funcs.glsl
src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp