llama.cpp/run.h at 3a0dcb39207a18ab3f8d825914d0c4359ae9736d - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00

Files

Thiago Padilha bf44faa0ee Remove direct access to std streams from "run"

The goal is to allow running "run" while connected to other streams,
such as TCP sockets.

Signed-off-by: Thiago Padilha <thiago@padilha.cc>

2023-03-22 14:34:18 -03:00

11 lines

193 B

C++

Raw Blame History

 #pragma once
 #include "llama.h"
 #include "utils.h"
 int run(llama_context * ctx,
         gpt_params params,
         std::istream & instream,
         FILE *outstream,
         FILE *errstream);