CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: increase LOAD_VEC_A to 8 (IQ1/IQ2) or 4 (IQ3) (#14485)

Browse Source 
Commit taken from remyoudompheng's PR https://github.com/ggml-org/llama.cpp/pull/12260

Co-authored-by: Rémy Oudompheng <remyoudompheng@gmail.com>
This commit is contained in:
Eve
2025-07-06 10:29:36 +00:00
committed by GitHub
parent e592be1575
commit 6491d6e4f1
2 changed files with 79 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
View File

@@ -360,9 +360,9 @@ void matmul_shaders(bool fp16, bool matmul_id, bool coopmat, bool coopmat2, bool
for (const auto& tname : type_names) {
std::string load_vec_quant = "2";
if ((tname == "q4_0") || (tname == "q4_1"))
if ((tname == "q4_0") || (tname == "q4_1") || (tname == "iq1_s") || (tname == "iq1_m") || (tname == "iq2_xxs") || (tname == "iq2_xs") || (tname == "iq2_s"))
load_vec_quant = "8";
else if ((tname == "q5_0") || (tname == "q5_1") || (tname == "q8_0") || (tname == "iq4_nl"))
else if ((tname == "q5_0") || (tname == "q5_1") || (tname == "q8_0") || (tname == "iq3_xxs") || (tname == "iq3_s") || (tname == "iq4_nl"))
load_vec_quant = "4";
if (tname == "bf16") {