Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-01 10:00:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	README.md
#	docs/backend/SYCL.md
#	examples/llava/README.md
#	examples/llava/clip.cpp
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/sycl/run-llama2.sh
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2025-02-26 18:44:45 +08:00
parent 50eae1ffeb 53e4db1012
commit 722fc2dbf1
79 changed files with 9330 additions and 5299 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/server/utils.hpp
+7 -2
View File
@@ -521,8 +521,13 @@ static json oaicompat_completion_params_parse(const json & body) {
throw std::runtime_error("Only one completion choice is allowed");
}
// Handle "echo" field
if (json_value(body, "echo", false)) {
throw std::runtime_error("Only no echo is supported");
}
// Params supported by OAI but unsupported by llama.cpp
static const std::vector<std::string> unsupported_params { "best_of", "echo", "suffix" };
static const std::vector<std::string> unsupported_params { "best_of", "suffix" };
for (const auto & param : unsupported_params) {
if (body.contains(param)) {
throw std::runtime_error("Unsupported param: " + param);
@@ -598,7 +603,7 @@ static json oaicompat_completion_params_parse(
inputs.tool_choice = common_chat_tool_choice_parse_oaicompat(json_value(body, "tool_choice", std::string("auto")));
inputs.json_schema = json_schema.is_null() ? "" : json_schema.dump();
inputs.grammar = grammar;
inputs.add_generation_prompt = true;
inputs.add_generation_prompt = json_value(body, "add_generation_prompt", true);
inputs.use_jinja = use_jinja;
inputs.parallel_tool_calls = json_value(body, "parallel_tool_calls", false);
inputs.extract_reasoning = reasoning_format != COMMON_REASONING_FORMAT_NONE;