Microsoft MVP성태의 닷넷 이야기
닷넷: 2353. C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용 [링크 복사], [링크+제목 복사],
조회: 594
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)
13994정성태8/12/2025265오류 유형: 977. SQL Server - User, group, or role '...' already exists in the current database. (Microsoft SQL Server, Error: 15023)
13993정성태8/11/2025503오류 유형: 976. Microsoft.ML.OnnxRuntimeGenAI 패키지 사용 시 "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.") 오류
13992정성태8/11/2025594닷넷: 2353. C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용파일 다운로드1
13991정성태8/9/2025614오류 유형: 975. winget - Foundry Local 패키지 업데이트가 안 되는 문제
13990정성태8/8/2025575Windows: 283. Time zone 설정이 없는 Windows Server 2025
13989정성태8/8/2025711닷넷: 2352. C# - Windows S-mode 환경인지 체크하는 방법파일 다운로드1
13988정성태8/8/2025800오류 유형: 974. 비주얼 스튜디오 업데이트 시 잠김 파일 경고 - Visual Studio Standard Collector Service 150 (VSStandardCollectorService150)
13987정성태8/7/2025675닷넷: 2351. C# 14 - (7) event와 생성자에도 partial 메서드 적용파일 다운로드1
13986정성태8/6/2025869닷넷: 2350. C# 14 - (6) 람다 매개 변수에 접근자가 있는 경우에도 타입 생략 가능파일 다운로드1
13985정성태8/6/2025968오류 유형: 973. "wsl --install" 명령어 수행 시 "The server name or address could not be resolved"
13984정성태8/6/2025977Windows: 282. 윈도우 운영체제에 추가된 ssh 서버(Win32-OpenSSH)
13983정성태8/4/2025996오류 유형: 972. .NET 8 이상만 지원하는 Microsoft.Data.SqlClient 6.1.0 버전
13982정성태8/2/20251350개발 환경 구성: 753. CentOS 7 컨테이너 내에서 openssh 서버 호스팅
13981정성태8/1/2025961오류 유형: 971. CentOS 7에서 yum 사용 시 "Could not resolve host: mirrorlist.centos.org; Unknown error"
13980정성태7/31/20251074Linux: 119. eBPF - BPF_PROG_TYPE_CGROUP_SOCK 유형에서 정상 동작하지 않는 BPF_CORE_READ (2)
13979정성태7/30/20251426Linux: 118. eBPF - BPF_PROG_TYPE_CGROUP_SOCK 유형에서 정상 동작하지 않는 BPF_CORE_READ
13978정성태7/29/20251545오류 유형: 970. 파일 복사 시 "Data error (cyclic redundancy check). (0x80070017)" 에러
13977정성태7/28/20251857닷넷: 2349. C# 14 - (5) 문자열 리터럴을 utf-8 인코딩으로 저장파일 다운로드1
13976정성태7/25/20251730닷넷: 2348. C# - 카카오 카나나 모델 + Microsoft.ML.OnnxRuntimeGenAI 예제파일 다운로드1
13975정성태7/23/20251630닷넷: 2347. C# 14 - (4) 형식 인자가 없는 제네릭 타입의 nameof 지원파일 다운로드1
13974정성태7/22/20251692닷넷: 2346. C# 14 - (3) Span 타입과 배열 간의 암시적 형변환파일 다운로드1
13973정성태7/21/20251506닷넷: 2345. C# - 배열 및 Span의 공변성파일 다운로드1
13972정성태7/21/20251482닷넷: 2344. C#의 Identity conversion 의미파일 다운로드1
13971정성태7/17/20251537닷넷: 2343. C# 14 - (2) 속성 구문에서 문맥 키워드로 추가되는 field 예약어파일 다운로드1
13970정성태7/17/20251485닷넷: 2342. C# 14 - (1) (예약)
[1]  2  3  4  5  6  7  8  9  10  11  12  13  14  15  ...