Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/musa.Dockerfile
#	.github/workflows/build.yml
#	README.md
#	ci/README.md
#	docs/docker.md
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-arg-parser.cpp
This commit is contained in:
Concedo
2025-05-21 23:12:22 +08:00
parent 9f976e9c65 33983057d0
commit da7fd4aa57
22 changed files with 270 additions and 384 deletions
Download Patch File Download Diff File Expand all files Collapse all files
otherarch/embeddings_adapter.cpp
+2 -2
View File
@@ -149,7 +149,7 @@ bool embeddingstype_load_model(const embeddings_load_model_inputs inputs)
}
std::vector<int> tmp = {1, 2, 3, 4};
llama_kv_cache_clear(embeddings_ctx);
llama_kv_self_clear(embeddings_ctx);
auto er = llama_decode(embeddings_ctx, llama_batch_get_one(tmp.data(), tmp.size()));
if(er!=0)
{
@@ -190,7 +190,7 @@ embeddings_generation_outputs embeddingstype_generate(const embeddings_generatio
double timetaken = 0;
timer_start();
llama_kv_cache_clear(embeddings_ctx);
llama_kv_self_clear(embeddings_ctx);
std::string prompt = inputs.prompt;
// max batch size