Microsoft MVP성태의 닷넷 이야기
닷넷: 2353. C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용 [링크 복사], [링크+제목 복사],
조회: 640
글쓴 사람
정성태 (seongtaejeong at gmail.com)
홈페이지
첨부 파일

(시리즈 글이 6개 있습니다.)
개발 환경 구성: 748. Windows + Foundry Local - 로컬에서 AI 모델 활용
; https://www.sysnet.pe.kr/2/0/13943

닷넷: 2337. C# - Hugging Face에 공개된 LLM 모델을 Foundry Local에서 사용하는 방법
; https://www.sysnet.pe.kr/2/0/13954

닷넷: 2338. C# / Foundry Local - Phi-4-multimodal 모델을 사용하는 방법
; https://www.sysnet.pe.kr/2/0/13957

닷넷: 2339. C# - Phi-4-multimodal 모델의 GPU 가속 방법 (ORT 사용)
; https://www.sysnet.pe.kr/2/0/13958

닷넷: 2348. C# - 카카오 카나나 모델 + Microsoft.ML.OnnxRuntimeGenAI 예제
; https://www.sysnet.pe.kr/2/0/13976

닷넷: 2353. C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용
; https://www.sysnet.pe.kr/2/0/13992




C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용

오호~~~ 최근 OpenAI에서 GPT OSS 20B 모델을 공개했는데요, Hugging Face에도 올라온 상태입니다.

openai/gpt-oss-20b
; https://huggingface.co/openai/gpt-oss-20b/blob/main/config.json

아쉽게도 "GptOssForCausalLM" 구조라 olive를 이용한 ONNX 포맷으로의 전환이 안 되는 유형이었는데, 마이크로소프트에서 발 빠르게 이것을 Foundry Local에 기본 지원 모델로 포함시켰기 때문에,

Available today: gpt-oss-20B Model on Windows with GPU Acceleration – further pushing the boundaries on the edge
; https://blogs.windows.com/windowsdeveloper/2025/08/05/available-today-gpt-oss-20b-model-on-windows-with-gpu-acceleration-further-pushing-the-boundaries-on-the-edge/

지난 글에서 설명한 방법대로 C#에서도 손쉽게 접근할 수 있습니다.

Windows + Foundry Local - 로컬에서 AI 모델 활용
; https://www.sysnet.pe.kr/2/0/13943




그래도 한번 실습을 해볼까요? ^^ 일단 olive 변환은 할 수 없으니, Foundry Local을 이용해 다음과 같이 다운로드할 수 있습니다.

C:\temp> foundry model download gpt-oss-20B
Downloading gpt-oss-20b-cuda-gpu...
[####################################] 100.00 % [Time remaining: about 0s]        36.9 MB/s
Tips:
- To find model cache location use: foundry cache location
- To find models already downloaded use: foundry cache ls

이후 OpenAI 패키지로 Foundry Local과 연동해 이런 식으로 코딩할 수 있습니다.

using OpenAI;
using OpenAI.Chat;
using System.ClientModel;

namespace ConsoleApp1;

internal class Program
{
    // Install-Package OpenAI 
    static void Main(string[] args)
    {
        string ep = "http://localhost:5273/v1";
        string key = "OPENAI_API_KEY";
        string alias = "gpt-oss-20b-cuda-gpu";

        OpenAIClientOptions options = new OpenAIClientOptions();
        options.Endpoint = new Uri(ep);

        ApiKeyCredential akc = new ApiKeyCredential(key);
        ChatClient client = new(alias, akc, options);

        ChatCompletion completion = client.CompleteChat("하늘이 파란 이유는?'");

        foreach (var message in completion.Content)
        {
            Console.WriteLine($"[{message.Kind}]: {message.Text}");
        }
    }
}

/* 실행 결과:

[Text]: <|channel|>analysis<|message|>The user says: "하늘이 파란 이유는?" in Korean, which translates to "The reason why the sky is blue?" The question is likely about the reason behind Rayleigh scattering, color of sky because of scattering of shorter wavelengths of visible light off atmosphere, etc.

We need to respond. The user didn't give any context besides asking. They just say in Korean: "The reason the sky is blue?" So answer: It's due to Rayleigh scattering causing blue light to be scattered more.

We can provide explanation: solar light: white, but Earth's atmosphere scatters more of blue wavelengths, causing blue sky.

So just answer like: "태양빛이 투과하면서 대기 중 분자와 아주 작은 입자에 의해 산란된 파장에서 가장 짧은 파장이 산란이 가장 잘 일어나므로..." or we can keep simple.

We can also mention the "Huygens–Fresnel principle" or "Mie scattering
*/

참고로, 모델 용량이 11GB 정도여서 그런지 초기 로딩 시간이 꽤 걸리는군요. ^^

(첨부 파일은 이 글의 예제 코드를 포함합니다.)




Foundry Local을 통해 다운로드한 모델의 경우 .\Microsoft\gpt-oss-20b-cuda-gpu\v1 디렉터리에 genai_config.json 파일이 함께 있습니다. 아하... 그렇다면 Microsoft.ML.OnnxRuntimeGenAI 패키지를 이용하는 것도 가능하다는 의미일 텐데요,

using Microsoft.ML.OnnxRuntimeGenAI;
using System.Reflection;
using System.Reflection.Emit;

namespace ConsoleApp2;

internal class Program
{
    // Install-Package Microsoft.ML.OnnxRuntimeGenAI.CUDA

    static void Main(string[] args)
    {
        // cuDNN 필요
        string? path = Environment.GetEnvironmentVariable("PATH");
        path += @";C:\Program Files\NVIDIA\CUDNN\v9.10\bin\12.9";
        Environment.SetEnvironmentVariable("PATH", path);

        string modelPath = @"C:\foundry_cache\Microsoft\gpt-oss-20b-cuda-gpu\v1";

        Console.Write("Loading model from " + modelPath + "...");
        using Model model = new(modelPath);
        Console.Write("Done\n");
        using Tokenizer tokenizer = new(model);
        using TokenizerStream tokenizerStream = tokenizer.CreateStream();

        while (true)
        {
            Console.Write("User:");

            string prompt = "<|im_start|>user\n" +
                            Console.ReadLine() +
                            "<|im_end|>\n<|im_start|>assistant\n";
            var sequences = tokenizer.Encode(prompt);

            using GeneratorParams gParams = new GeneratorParams(model);
            gParams.SetSearchOption("max_length", 2400);
            using Generator generator = new(model, gParams);
            generator.AppendTokenSequences(sequences);

            Console.Out.Write("\nAI:");
            while (!generator.IsDone())
            {
                generator.GenerateNextToken();
                var token = generator.GetSequence(0)[^1];
                Console.Out.Write(tokenizerStream.Decode(token));
                Console.Out.Flush();
            }
            Console.WriteLine();
        }
    }
}

아쉽게도 실행해 보면 이런 오류가 발생합니다.

Loading model from C:\foundry_cache\Microsoft\gpt-oss-20b-cuda-gpu\v1...Unhandled exception. Microsoft.ML.OnnxRuntimeGenAI.OnnxRuntimeGenAIException: Load model from E:\foundry_cache\Microsoft\gpt-oss-20b-cuda-gpu\v1\model.onnx failed:This is an invalid model. In Node, ("/model/layers.0/attn/GroupQueryAttention", GroupQueryAttention, "com.microsoft", -1) : ("/model/layers.0/attn/qkv_proj/Add/output_0": tensor(float16),"","","past_key_values.0.key": tensor(float16),"past_key_values.0.value": tensor(float16),"/model/attn_mask_reformat/attn_mask_subgraph/Sub/Cast/output_0": tensor(int32),"/model/attn_mask_reformat/attn_mask_subgraph/Gather/Cast/output_0": tensor(int32),"cos_cache": tensor(float16),"sin_cache": tensor(float16),"","","model.layers.0.attn.sinks": tensor(float16),) -> ("/model/layers.0/attn/GroupQueryAttention/output_0": tensor(float16),"present.0.key": tensor(float16),"present.0.value": tensor(float16),) , Error Node(/model/layers.0/attn/GroupQueryAttention) with schema(com.microsoft::GroupQueryAttention:1) has input size 12 not in range [min=7, max=11].
at Microsoft.ML.OnnxRuntimeGenAI.Model..ctor(String modelPath)
at ConsoleApp2.Program.Main(String[] args)


음... 아마도 Microsoft.ML.OnnxRuntimeGenAI 패키지가 업데이트되기를 기다려야 할 것 같습니다. ^^ (기록을 보니까 불과 5일 전에 0.9.0 업데이트가 되었는데 그 버전이 안 됩니다.)




혹시나 Foundry Local에서 gpt-oss-20B 모델을 찾지 못한다고 나오면?

C:\foundry_cache> foundry model run gpt-oss-20B
Exception: Model gpt-oss-20B not found

지난 버전의 Foundry Local을 사용하고 있는 경우인데요, 최신 버전으로 업데이트하면 됩니다.




[이 글에 대해서 여러분들과 의견을 공유하고 싶습니다. 틀리거나 미흡한 부분 또는 의문 사항이 있으시면 언제든 댓글 남겨주십시오.]







[최초 등록일: ]
[최종 수정일: 8/12/2025]

Creative Commons License
이 저작물은 크리에이티브 커먼즈 코리아 저작자표시-비영리-변경금지 2.0 대한민국 라이센스에 따라 이용하실 수 있습니다.
by SeongTae Jeong, mailto:techsharer at outlook.com

비밀번호

댓글 작성자
 




... [16]  17  18  19  20  21  22  23  24  25  26  27  28  29  30  ...
NoWriterDateCnt.TitleFile(s)
13620정성태5/9/202410996VS.NET IDE: 190. Visual Studio가 node.exe를 경유해 Edge.exe를 띄우는 경우
13619정성태5/7/202411773닷넷: 2259. C# - decimal 저장소의 비트 구조 [2]파일 다운로드1
13618정성태5/6/202410374닷넷: 2258. C# - double (배정도 실수) 저장소의 비트 구조파일 다운로드1
13617정성태5/5/202412883닷넷: 2257. C# - float (단정도 실수) 저장소의 비트 구조파일 다운로드1
13616정성태5/3/202410385닷넷: 2256. ASP.NET Core 웹 사이트의 HTTP/HTTPS + Dual mode Socket (IPv4/IPv6) 지원 방법파일 다운로드1
13615정성태5/3/202412986닷넷: 2255. C# 배열을 Numpy ndarray 배열과 상호 변환
13614정성태5/2/202412777닷넷: 2254. C# - COM 인터페이스의 상속 시 중복으로 메서드를 선언
13613정성태5/1/202410605닷넷: 2253. C# - Video Capture 장치(Camera) 열거 및 지원 포맷 조회파일 다운로드1
13612정성태4/30/202412293오류 유형: 902. Visual Studio - error MSB3021: Unable to copy file
13611정성태4/29/202410824닷넷: 2252. C# - GUID 타입 전용의 UnmanagedType.LPStruct - 두 번째 이야기파일 다운로드1
13610정성태4/28/202412347닷넷: 2251. C# - 제네릭 인자를 가진 타입을 생성하는 방법 - 두 번째 이야기
13609정성태4/27/202412006닷넷: 2250. PInvoke 호출 시 참조 타입(class)을 마샬링하는 [IN], [OUT] 특성파일 다운로드1
13608정성태4/26/202412860닷넷: 2249. C# - 부모의 필드/프로퍼티에 대해 서로 다른 자식 클래스 간에 Reflection 접근이 동작할까요?파일 다운로드1
13607정성태4/25/202412868닷넷: 2248. C# - 인터페이스 타입의 다중 포인터를 인자로 갖는 C/C++ 함수 연동
13606정성태4/24/202412921닷넷: 2247. C# - tensorflow 연동 (MNIST 예제)파일 다운로드1
13605정성태4/23/202414345닷넷: 2246. C# - Python.NET을 이용한 파이썬 소스코드 연동파일 다운로드1
13604정성태4/22/202410485오류 유형: 901. Visual Studio - Unable to set the next statement. Set next statement cannot be used in '[Exception]' call stack frames.
13603정성태4/21/202413424닷넷: 2245. C# - IronPython을 이용한 파이썬 소스코드 연동파일 다운로드1
13602정성태4/20/202411605닷넷: 2244. C# - PCM 오디오 데이터를 연속(Streaming) 재생 (Windows Multimedia)파일 다운로드1
13601정성태4/19/202412001닷넷: 2243. C# - PCM 사운드 재생(NAudio)파일 다운로드1
13600정성태4/18/202413498닷넷: 2242. C# - 관리 스레드와 비관리 스레드
13599정성태4/17/202413200닷넷: 2241. C# - WAV 파일의 PCM 사운드 재생(Windows Multimedia)파일 다운로드1
13598정성태4/16/202413330닷넷: 2240. C# - WAV 파일 포맷 + LIST 헤더파일 다운로드2
13597정성태4/15/202410948닷넷: 2239. C# - WAV 파일의 PCM 데이터 생성 및 출력파일 다운로드1
13596정성태4/14/202411916닷넷: 2238. C# - WAV 기본 파일 포맷파일 다운로드1
13595정성태4/13/202412484닷넷: 2237. C# - Audio 장치 열기 (Windows Multimedia, NAudio)파일 다운로드1
... [16]  17  18  19  20  21  22  23  24  25  26  27  28  29  30  ...