Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

🌐 [i18n-KO] Translated eetq.md to Korean #32352

Merged
merged 9 commits into from
Aug 8, 2024

Conversation

jun048098
Copy link
Contributor

@jun048098 jun048098 commented Jul 31, 2024

What does this PR do?

Translated the eetq.md file of the documentation to Korean.
Thank you in advance for your review.

Part of #20179

Before reviewing

  • Check for missing / redundant translations (번역 누락/중복 검사)
  • Grammar Check (맞춤법 검사)
  • Review or Add new terms to glossary (용어 확인 및 추가)
  • Check Inline TOC (e.g. [[lowercased-header]])
  • Check live-preview for gotchas (live-preview로 정상작동 확인)

Who can review? (Initial)

@jun048098, @yijun-lee, @mreraser, @shinhyunji36, @heuristicwave

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review? (Final)

@stevhliu May you please review this PR?

@jun048098 jun048098 marked this pull request as ready for review July 31, 2024 15:56
Copy link
Contributor

@junejae junejae left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@jun048098
아직 OSSCA 팀원들에게 리뷰/검토되지 않은 PR입니다. PR의 상태를 Draft로 변경 부탁드립니다.

This PR has never been reviewed by OSSCA members, Please change your PR's status to Draft.

@jun048098 jun048098 marked this pull request as draft August 3, 2024 16:26

# EETQ [[eetq]]

[EETQ](https://github.com/NetEase-FuXi/EETQ) 라이브러리는 NVIDIA GPU에 대해 int8 채널별(per-channel) weight-only quantization을 지원합니다. 고성능 GEMM 및 GEMV 커널은 FasterTransformer 및 TensorRT-LLM에서 가져왔습니다. 캘리브레이션 데이터셋이 필요 없으며, 모델을 사전에 양자화할 필요도 없습니다. 또한, 채널별 양자화(per-channel quantization) 덕분에 정확도 저하가 미미합니다.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
[EETQ](https://github.com/NetEase-FuXi/EETQ) 라이브러리는 NVIDIA GPU에 대해 int8 채널별(per-channel) weight-only quantization을 지원합니다. 고성능 GEMM 및 GEMV 커널은 FasterTransformer 및 TensorRT-LLM에서 가져왔습니다. 캘리브레이션 데이터셋이 필요 없으며, 모델을 사전에 양자화할 필요도 없습니다. 또한, 채널별 양자화(per-channel quantization) 덕분에 정확도 저하가 미미합니다.
[EETQ](https://github.com/NetEase-FuXi/EETQ) 라이브러리는 NVIDIA GPU에 대해 int8 채널별(per-channel) 가중치 전용 양자화(weight-only quantization)를 지원합니다.
고성능 GEMM 및 GEMV 커널은 FasterTransformer 및 TensorRT-LLM에서 가져왔습니다. 보정(calibration) 데이터셋이 필요 없으며, 모델을 사전에 양자화할 필요도 없습니다. 또한, 채널별 양자화(per-channel quantization) 덕분에 정확도 저하가 미미합니다.

개행과 calibration datasets에 대한 의견을 남겨두었습니다.

Copy link
Contributor Author

@jun048098 jun048098 Aug 6, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

weight-only quantization 은 intel에서 제공하는 extension이라 번역이 적절한지 고민하고 있었습니다
#링크

추가로 검색 결과 calibration은 교정으로 사용하는 듯합니다. 교정으로 개행하겠습니다
#링크

@heuristicwave
Copy link
Contributor

@jun048098 Before reviewing 체크리스트도 체크 부탁드려요~

Copy link
Contributor

@shinhyunji36 shinhyunji36 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

다른 분들이 리뷰해주신 부분 외에 특별한 리뷰 사항을 발견하지 못했습니다! 고생 하셨습니다 😃

Co-authored-by: Jiwook Han <33192762+mreraser@users.noreply.github.com>
Copy link
Contributor

@yijun-lee yijun-lee left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

개행 이외에는 딱히 수정할 곳이 없어보입니다! 수고하셨습니다.

docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
```

또는 소스 코드 https://github.com/NetEase-FuXi/EETQ 에서 설치할 수 있습니다. EETQ는 CUDA 기능이 8.9 이하이고 7.0 이상이어야 합니다.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

22, 26, 28, 37번 라인에 원문과 다른 개행이 있는 것 같습니다.

docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
Copy link
Contributor Author

@jun048098 jun048098 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

개행 제거

docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
docs/source/ko/quantization/eetq.md Outdated Show resolved Hide resolved
@jun048098 jun048098 marked this pull request as ready for review August 6, 2024 12:59
@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Copy link
Member

@stevhliu stevhliu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice job! Once we resolve the conflict, we can merge 🤗

@stevhliu stevhliu merged commit e0396bd into huggingface:main Aug 8, 2024
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

8 participants