CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : (refactoring) do not rely on JSON internally (#10643)

Browse Source 
* server : (refactoring) reduce usage of json internally

* move all response types to struct

* wip [no ci]

* many fixes

* add virtual function

* fix index

* minor style fix

* add std::move

* refactor handle_completions_generic

* add virtual functions

* remove server.hpp

* clarify server_sent_event RFC specs

* apply review comments

* fix model_alias and completion_probabilities

* small clean up

* remove virtual for to_json_oai_compat()

* naming oai_compat --> oaicompat

* fix unwanted recursive call

* update docs
This commit is contained in:
Xuan Son Nguyen
2024-12-06 11:14:32 +01:00
committed by GitHub
parent 7736837d62
commit 6c5bc0625f
8 changed files with 985 additions and 697 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.h
View File

@@ -215,7 +215,7 @@ struct common_params {
struct common_params_speculative speculative;
std::string model = ""; // model path // NOLINT
std::string model_alias = "unknown"; // model alias // NOLINT
std::string model_alias = ""; // model alias // NOLINT
std::string model_url = ""; // model url to download // NOLINT
std::string hf_token = ""; // HF token // NOLINT
std::string hf_repo = ""; // HF repo // NOLINT