Microsoft MVP성태의 닷넷 이야기
닷넷: 2353. C# - Foundry Local을 이용한 gpt-oss-20b 모델 사용 [링크 복사], [링크+제목 복사],
조회: 714
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)
13523정성태1/12/202413393오류 유형: 889. Visual Studio - error : A project with that name is already opened in the solution.
13522정성태1/11/202414154닷넷: 2200. C# - HttpClient.PostAsJsonAsync 호출 시 "Transfer-Encoding: chunked" 대신 "Content-Length" 헤더 처리
13521정성태1/11/202412263닷넷: 2199. C# - 한국투자증권 KIS Developers OpenAPI의 WebSocket Ping, Pong 처리
13520정성태1/10/202412323오류 유형: 888. C# - Unable to resolve service for type 'Microsoft.Extensions.ObjectPool.ObjectPool`....' [1]
13519정성태1/10/202411538닷넷: 2198. C# - Reflection을 이용한 ClientWebSocket의 Ping 호출파일 다운로드1
13518정성태1/9/202413134닷넷: 2197. C# - ClientWebSocket의 Ping, Pong 처리
13517정성태1/8/202411332스크립트: 63. Python - 공개 패키지를 이용한 위성 이미지 생성 (pystac_client, odc.stac)
13516정성태1/7/202413164닷넷: 2196. IIS - AppPool의 "Disable Overlapped Recycle" 옵션의 부작용
13515정성태1/6/202411495닷넷: 2195. async 메서드 내에서 C# 7의 discard 구문 활용 사례 [1]
13514정성태1/5/202411472개발 환경 구성: 702. IIS - AppPool의 "Disable Overlapped Recycle" 옵션
13513정성태1/5/202412942닷넷: 2194. C# - WebActivatorEx / System.Web의 PreApplicationStartMethod 특성
13512정성태1/4/202413727개발 환경 구성: 701. IIS - w3wp.exe 프로세스의 ASP.NET 런타임을 항상 Warmup 모드로 유지하는 preload Enabled 설정
13511정성태1/4/202413078닷넷: 2193. C# - ASP.NET Web Application + OpenAPI(Swashbuckle) 스펙 제공
13510정성태1/3/202412948닷넷: 2192. C# - 특정 실행 파일이 있는지 확인하는 방법 (Linux)
13509정성태1/3/202413978오류 유형: 887. .NET Core 2 이하의 프로젝트에서 System.Runtime.CompilerServices.Unsafe doesn't support netcoreapp2.0.
13508정성태1/3/202415751오류 유형: 886. ORA-28000: the account is locked
13507정성태1/2/202413535닷넷: 2191. C# - IPGlobalProperties를 이용해 netstat처럼 사용 중인 Socket 목록 구하는 방법파일 다운로드1
13506정성태12/29/202312128닷넷: 2190. C# - 닷넷 코어/5+에서 달라지는 System.Text.Encoding 지원
13505정성태12/27/202315821닷넷: 2189. C# - WebSocket 클라이언트를 닷넷으로 구현하는 예제 (System.Net.WebSockets)파일 다운로드1
13504정성태12/27/202315002닷넷: 2188. C# - ASP.NET Core SignalR로 구현하는 채팅 서비스 예제파일 다운로드1
13503정성태12/27/202313114Linux: 67. WSL 환경 + mlocate(locate) 도구의 /mnt 디렉터리 검색 문제
13502정성태12/26/202313917닷넷: 2187. C# - 다른 프로세스의 환경변수 읽는 예제파일 다운로드1
13501정성태12/25/202313189개발 환경 구성: 700. WSL + uwsgi - IPv6로 바인딩하는 방법
13500정성태12/24/202314211디버깅 기술: 194. Windbg - x64 가상 주소를 물리 주소로 변환
13498정성태12/23/202314742닷넷: 2186. 한국투자증권 KIS Developers OpenAPI의 C# 래퍼 버전 - eFriendOpenAPI NuGet 패키지
13497정성태12/22/202314125오류 유형: 885. Visual Studiio - error : Could not connect to the remote system. Please verify your connection settings, and that your machine is on the network and reachable.
... 16  17  18  19  [20]  21  22  23  24  25  26  27  28  29  30  ...