-
Notifications
You must be signed in to change notification settings - Fork 26.9k
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
Conversation
There was a problem hiding this 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.
docs/source/ko/quantization/eetq.md
Outdated
|
||
# 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. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
[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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@jun048098 Before reviewing 체크리스트도 체크 부탁드려요~ |
There was a problem hiding this 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>
There was a problem hiding this 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
``` | ||
|
||
또는 소스 코드 https://github.com/NetEase-FuXi/EETQ 에서 설치할 수 있습니다. EETQ는 CUDA 기능이 8.9 이하이고 7.0 이상이어야 합니다. | ||
|
There was a problem hiding this comment.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
개행 제거
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. |
There was a problem hiding this 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 🤗
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
[[lowercased-header]]
)Who can review? (Initial)
@jun048098, @yijun-lee, @mreraser, @shinhyunji36, @heuristicwave
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review? (Final)
@stevhliu May you please review this PR?