Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'd82b7a7c1d73c0674698d9601b1bbb0200933f29' into concedo_experimental

Browse Source 
# Conflicts:
#	ci/run.sh
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cuda/common.cuh
#	tests/CMakeLists.txt
This commit is contained in:
Concedo
2025-11-30 15:43:11 +08:00
parent 65a3b75dac d82b7a7c1d
commit bf5efcf86d
17 changed files with 1046 additions and 999 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/embedding/embedding.cpp
+4 -3
View File
@@ -104,12 +104,16 @@ int main(int argc, char ** argv) {
params.embedding = true;
// get max number of sequences per batch
const int n_seq_max = llama_max_parallel_sequences();
// if the number of prompts that would be encoded is known in advance, it's more efficient to specify the
// --parallel argument accordingly. for convenience, if not specified, we fallback to unified KV cache
// in order to support any number of prompts
if (params.n_parallel == 1) {
LOG_INF("%s: n_parallel == 1 -> unified KV cache is enabled\n", __func__);
params.kv_unified = true;
params.n_parallel = n_seq_max;
}
// utilize the full context
@@ -123,9 +127,6 @@ int main(int argc, char ** argv) {
params.n_ubatch = params.n_batch;
}
// get max number of sequences per batch
const int n_seq_max = llama_max_parallel_sequences();
llama_backend_init();
llama_numa_init(params.numa);