# 1단계:
brew install cactus-compute/cactus/cactus
# 2단계:
cactus transcribe
orcactus run

#include "cactus.h"
cactus_model_t model = cactus_init(
"path/to/weight/folder",
"path to txt or dir of txts for auto-rag",
false
);
const char* messages = R"([
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "My name is Henry Ndubuaku"}
])";
const char* options = R"({
"max_tokens": 50,
"stop_sequences": ["<|im_end|>"]
})";
char response[4096];
int result = cactus_complete(
model, // model handle
messages, // JSON chat messages
response, // response buffer
sizeof(response), // buffer size
options, // generation options
nullptr, // tools JSON
nullptr, // streaming callback
nullptr, // user data
nullptr, // pcm audio buffer
0 // pcm buffer size
);

{
"success": true, // 생성 성공
"error": null, // 실패 시 오류 상세 정보
"cloud_handoff": false, // 클라우드 모델 사용 여부 (true일 경우)
"response": "Hi there!",
"function_calls": [], // 파싱된 도구 호출
"confidence": 0.8193, // 모델 신뢰도
"time_to_first_token_ms": 45.23,
"total_time_ms": 163.67,
"prefill_tps": 1621.89,
"decode_tps": 168.42,
"ram_usage_mb": 245.67,
"prefill_tokens": 28,
"decode_tokens": 50,
"total_tokens": 78
}

#include "cactus.h"
CactusGraph graph;
auto a = graph.input({2, 3}, Precision::FP16);
auto b = graph.input({3, 4}, Precision::INT8);
auto x1 = graph.matmul(a, b, false);
auto x2 = graph.transpose(x1);
auto result = graph.matmul(b, x2, true);
float a_data[6] = {1.1f, 2.3f, 3.4f, 4.2f, 5.7f, 6.8f};
float b_data