Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

rm redundant includes

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-11-18 15:01:17 +01:00
parent 3b7946034c
commit ca993bad51
6 changed files with 59 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-common.h
-40
View File
@@ -42,11 +42,6 @@ using json = nlohmann::ordered_json;
#define SRV_ERR(fmt, ...) LOG_ERR("srv %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define SRV_DBG(fmt, ...) LOG_DBG("srv %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_INF(fmt, ...) LOG_INF("que %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_WRN(fmt, ...) LOG_WRN("que %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_ERR(fmt, ...) LOG_ERR("que %12.*s: " fmt, 12, __func__, __VA_ARGS__)
#define QUE_DBG(fmt, ...) LOG_DBG("que %12.*s: " fmt, 12, __func__, __VA_ARGS__)
using raw_buffer = std::vector<uint8_t>;
template <typename T>
@@ -71,41 +66,6 @@ enum stop_type {
STOP_TYPE_LIMIT,
};
// state diagram: https://github.com/ggml-org/llama.cpp/pull/9283
enum slot_state {
SLOT_STATE_IDLE,
SLOT_STATE_STARTED, // TODO: this state is only used for setting up the initial prompt processing; maybe merge it with launch_slot_with_task in the future
SLOT_STATE_PROCESSING_PROMPT,
SLOT_STATE_DONE_PROMPT,
SLOT_STATE_GENERATING,
};
enum server_state {
SERVER_STATE_LOADING_MODEL, // Server is starting up, model not fully loaded yet
SERVER_STATE_READY, // Server is ready and model is loaded
};
enum server_task_type {
SERVER_TASK_TYPE_COMPLETION,
SERVER_TASK_TYPE_EMBEDDING,
SERVER_TASK_TYPE_RERANK,
SERVER_TASK_TYPE_INFILL,
SERVER_TASK_TYPE_CANCEL,
SERVER_TASK_TYPE_NEXT_RESPONSE,
SERVER_TASK_TYPE_METRICS,
SERVER_TASK_TYPE_SLOT_SAVE,
SERVER_TASK_TYPE_SLOT_RESTORE,
SERVER_TASK_TYPE_SLOT_ERASE,
SERVER_TASK_TYPE_SET_LORA,
};
enum oaicompat_type {
OAICOMPAT_TYPE_NONE,
OAICOMPAT_TYPE_CHAT,
OAICOMPAT_TYPE_COMPLETION,
OAICOMPAT_TYPE_EMBEDDING,
};
// https://community.openai.com/t/openai-chat-list-of-error-codes-and-types/357791/11
enum error_type {
ERROR_TYPE_INVALID_REQUEST,