happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Correctly fetch q8_1 quantize pipeline in test as needed by 8a3519b (#19194)

This commit is contained in:
Simon Redman 2026-01-30 11:27:16 -05:00 committed by GitHub
parent dabaa2e77a
commit 13f3ebfae1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -11956,7 +11956,8 @@ static void ggml_vk_test_dequant_matmul(ggml_backend_vk_context * ctx, size_t m,
}
}
if (mmq) {
ggml_pipeline_request_descriptor_sets(ctx, ctx->device->pipeline_quantize_q8_1, num_it);
vk_pipeline pipeline_quantize_q8_1 = ggml_vk_get_quantize_pipeline(ctx, GGML_TYPE_Q8_1);
ggml_pipeline_request_descriptor_sets(ctx, pipeline_quantize_q8_1, num_it);
}
ggml_pipeline_allocate_descriptor_sets(ctx);