CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: initial support for IQ4_XS quantization (#11501)

Browse Source
This commit is contained in:
Rémy O
2025-02-06 07:09:59 +01:00
committed by GitHub
parent 1b598b3058
commit 8a7e3bf17a
13 changed files with 169 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-vulkan/vulkan-shaders/get_rows_quant.comp
View File

@@ -12,7 +12,7 @@ void main() {
const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;
#if defined(DATA_A_IQ2_XXS) || defined(DATA_A_IQ2_XS) || defined(DATA_A_IQ2_S) || defined(DATA_A_IQ3_XXS) || defined(DATA_A_IQ3_S) || defined(DATA_A_IQ4_NL)
#if defined(DATA_A_IQ2_XXS) || defined(DATA_A_IQ2_XS) || defined(DATA_A_IQ2_S) || defined(DATA_A_IQ3_XXS) || defined(DATA_A_IQ3_S) || defined(DATA_A_IQ4_XS) || defined(DATA_A_IQ4_NL)
init_iq_shmem(gl_WorkGroupSize);
#endif