vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-31 01:54:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.devops/cpu.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/nix/package.nix
#	.github/workflows/build-android.yml
#	.github/workflows/build-cann.yml
#	.github/workflows/build-msys.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/gguf-publish.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	docs/backend/CANN.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	scripts/sync_vendor.py
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-reasoning-budget.cpp
#	tools/cli/cli.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo 2026-03-30 20:45:38 +08:00
commit 42ad89cd86
74 changed files with 2403 additions and 331 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tools/completion/completion.cpp
View file

@ -147,13 +147,19 @@ int main(int argc, char ** argv) {
ctx = llama_init->context();
model = llama_init->model();
smpl = llama_init->sampler(0);
if (ctx == NULL) {
LOG_ERR("%s: error: unable to create context\n", __func__);
return 1;
}
if (model == NULL) {
LOG_ERR("%s: error: unable to load model\n", __func__);
return 1;
}
smpl = llama_init->sampler(0);
llama_memory_t mem = llama_get_memory(ctx);
const llama_vocab * vocab = llama_model_get_vocab(model);
@ -696,7 +702,7 @@ int main(int argc, char ** argv) {
if (!common_prompt_batch_decode(ctx, embd, n_past, params.n_batch, path_session, save_now)) {
return 1;
}
session_tokens.insert(session_tokens.end(), embd.begin(), embd.begin());
session_tokens.insert(session_tokens.end(), embd.begin(), embd.end());
n_session_consumed = session_tokens.size();
session_do_save = false;