vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 08:00:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build-cross.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	examples/llama.android/lib/src/main/cpp/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync_vendor.py
#	tests/test-chat.cpp
#	tests/test-mtmd-c-api.c
#	tools/server/README.md
This commit is contained in:
Concedo 2026-04-20 20:19:11 +08:00
commit cd6788007e
86 changed files with 1384 additions and 1240 deletions
Download patch file Download diff file Expand all files Collapse all files

38
common/common.cpp
View file

@ -1388,7 +1388,7 @@ common_init_result_ptr common_init_from_params(common_params & params) {
common_init_result::~common_init_result() = default;
std::string get_model_endpoint() {
std::string common_get_model_endpoint() {
const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
// We still respect the use of environment-variable "HF_ENDPOINT" for backward-compatibility.
const char * hf_endpoint_env = getenv("HF_ENDPOINT");
@ -1403,6 +1403,42 @@ std::string get_model_endpoint() {
return model_endpoint;
}
common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx) {
auto * mem = llama_get_memory(ctx);
if (mem == nullptr) {
return COMMON_CONTEXT_SEQ_RM_TYPE_NO;
}
common_context_seq_rm_type res = COMMON_CONTEXT_SEQ_RM_TYPE_PART;
llama_memory_clear(mem, true);
// eval 2 tokens to check if the context is compatible
std::vector<llama_token> tmp;
tmp.push_back(0);
tmp.push_back(0);
int ret = llama_decode(ctx, llama_batch_get_one(tmp.data(), tmp.size()));
if (ret != 0) {
LOG_ERR("%s: llama_decode() failed: %d\n", __func__, ret);
res = COMMON_CONTEXT_SEQ_RM_TYPE_NO;
goto done;
}
// try to remove the last tokens
if (!llama_memory_seq_rm(mem, 0, 1, -1)) {
LOG_WRN("%s: the target context does not support partial sequence removal\n", __func__);
res = COMMON_CONTEXT_SEQ_RM_TYPE_FULL;
goto done;
}
done:
llama_memory_clear(mem, true);
llama_synchronize(ctx);
return res;
}
void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora) {
std::vector<llama_adapter_lora *> loras;
std::vector<float> scales;