Microsoft MVP성태의 닷넷 이야기
닷넷: 2353. C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용 [링크 복사], [링크+제목 복사],
조회: 627
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
 




1  2  3  [4]  5  6  7  8  9  10  11  12  13  14  15  ...
NoWriterDateCnt.TitleFile(s)
13922정성태5/3/20253870스크립트: 73. 파이썬 - Windows embeddable package 버전에서 tkinter 환경 구성
13921정성태5/3/20254159오류 유형: 952. 듀얼 채널 메모리 정렬을 지키지 않은 컴퓨터의 Windows 비정상 종료 현상(Blue Screen) [2]
13920정성태5/3/20254615오류 유형: 951. Typed DataSet 생성 중 "Failed to open a connection to the database" 오류
13919정성태5/2/20253645VS.NET IDE: 201. C# - Typed DataSet(XSD)를 위한 연결 문자열 암호화 [1]파일 다운로드1
13918정성태5/2/20254494VS.NET IDE: 200. C# - app.config 파일의 출력을 Configuration(Debug/Release)에 따라 제어하는 방법파일 다운로드1
13917정성태4/30/20253191VS.NET IDE: 199. Directory.Build.props에 정의한 속성에 대해 Condition 제약으로 값을 변경하는 방법
13916정성태4/23/20252584디버깅 기술: 221. WinDbg 분석 사례 - ASP.NET HttpCookieCollection을 다중 스레드에서 사용할 경우 무한 루프 현상 - 두 번째 이야기
13915정성태4/13/20254639닷넷: 2331. C# - 실행 시에 메서드 가로채기 (.NET 9)파일 다운로드1
13914정성태4/11/20255146디버깅 기술: 220. windbg 분석 사례 - x86 ASP.NET 웹 응용 프로그램의 CPU 100% 현상 (4)
13913정성태4/10/20253077오류 유형: 950. Process Explorer - 64비트 윈도우에서 32비트 프로세스의 덤프를 뜰 때 "Error writing dump file: Access is denied." 오류
13912정성태4/9/20252751닷넷: 2330. C# - 실행 시에 메서드 가로채기 (.NET 5 ~ .NET 8)파일 다운로드1
13911정성태4/8/20253372오류 유형: 949. WinDbg - .NET Core/5+ 응용 프로그램 디버깅 시 sos 확장을 자동으로 로드하지 못하는 문제
13910정성태4/8/20253410디버깅 기술: 219. WinDbg - 명령어 내에서 환경 변수 사용법
13909정성태4/7/20255182닷넷: 2329. C# - 실행 시에 메서드 가로채기 (.NET Framework 4.8)파일 다운로드1
13908정성태4/2/20255348닷넷: 2328. C# - MailKit: SMTP, POP3, IMAP 지원 라이브러리
13907정성태3/29/20255746VS.NET IDE: 198. (OneDrive, Dropbox 등의 공유 디렉터리에 있는) C# 프로젝트의 출력 경로 변경하기
13906정성태3/27/20255928닷넷: 2327. C# - 초기화되지 않은 메모리에 접근하는 버그?파일 다운로드1
13905정성태3/26/20255932Windows: 281. C++ - Windows / Critical Section의 안정화를 위해 도입된 "Keyed Event"파일 다운로드1
13904정성태3/25/20254771디버깅 기술: 218. Windbg로 살펴보는 Win32 Critical Section파일 다운로드1
13903정성태3/24/20253572VS.NET IDE: 197. (OneDrive, Dropbox 등의 공유 디렉터리에 있는) C++ 프로젝트의 출력 경로 변경하기
13902정성태3/24/20254274개발 환경 구성: 742. Oracle - 테스트용 hr 계정 및 데이터 생성파일 다운로드1
13901정성태3/9/20254600Windows: 280. Hyper-V의 3가지 Thread Scheduler (Classic, Core, Root)
13900정성태3/8/20256062스크립트: 72. 파이썬 - SQLAlchemy + oracledb 연동
13899정성태3/7/20253497스크립트: 71. 파이썬 - asyncio의 ContextVar 전달
13898정성태3/5/20254548오류 유형: 948. Visual Studio - Proxy Authentication Required: dotnetfeed.blob.core.windows.net
13897정성태3/5/20256055닷넷: 2326. C# - PowerShell과 연동하는 방법 (두 번째 이야기)파일 다운로드1
1  2  3  [4]  5  6  7  8  9  10  11  12  13  14  15  ...