🌐 [i18n-KO] Translated fp_quant to Korean#39901
Draft
maximizemaxwell wants to merge 7 commits into
Draft
Conversation
nevertmr
reviewed
Aug 5, 2025
| > [!TIP] | ||
| > FP-Quant로 **사전 양자화된** 모델은 ISTA-DASLab의 [공식 컬렉션](https://huggingface.co/collections/ISTA-DASLab/fp-quant-6877c186103a21d3a02568ee)에서 확인하실 수 있습니다. | ||
|
|
||
| ## torch.compile |
Contributor
There was a problem hiding this comment.
Suggested change
| ## torch.compile | |
| ## torch.compile[[torchcompile]] |
TOC 추가하였습니다.
Co-authored-by: Minseo Kim <75977640+luckyvickyricky@users.noreply.github.com>
Co-authored-by: Minseo Kim <75977640+luckyvickyricky@users.noreply.github.com>
Co-authored-by: Minseo Kim <75977640+luckyvickyricky@users.noreply.github.com>
chelsseeey
reviewed
Aug 7, 2025
|
|
||
| 커널을 실행하려면 **Blackwell 세대 GPU가 필수**입니다. 런타임 지원은 [QuTLASS](https://github.com/IST-DASLab/qutlass) 라이브러리와 경량 PyTorch 인터페이스인 [`fp_quant`](https://github.com/IST-DASLab/FP-Quant/tree/master/inference_lib)로 구현되어 있습니다. 전자는 **소스에서 직접 설치**하시길 권장하며, 후자는 `pip install fp_quant`로 설치하면 됩니다. | ||
|
|
||
| Blackwell 세대 GPU가 **없으신** 경우에는 `quantization_config=FPQuantConfig(pseudoquant=True)` 옵션을 통해 QuTLASS 설치 없이도 양자화를 **완전히 에뮬레이션**할 수 있습니다. 속도 향상은 없지만, 양자화 효과를 동일하게 재현합니다. |
Contributor
There was a problem hiding this comment.
Suggested change
| Blackwell 세대 GPU가 **없으신** 경우에는 `quantization_config=FPQuantConfig(pseudoquant=True)` 옵션을 통해 QuTLASS 설치 없이도 양자화를 **완전히 에뮬레이션**할 수 있습니다. 속도 향상은 없지만, 양자화 효과를 동일하게 재현합니다. | |
| Blackwell 세대 GPU가 **없으신** 경우에는 `quantization_config=FPQuantConfig(pseudoquant=True)` 옵션을 통해 [QuTLASS](https://github.com/IST-DASLab/qutlass) 설치 없이도 양자화를 사용할 수 있습니다. 이 경우 속도 향상은 없지만, 양자화 효과를 동일하게 재현합니다. |
[QuTLASS] 링크 추가하였습니다.
Member
There was a problem hiding this comment.
Just a note that pseudoquant is an incorrect argument name in the original doc, it should be pseudoquantization.
chelsseeey
reviewed
Aug 7, 2025
|
|
||
| ## 속도 향상(Speedups)[[speedups]] | ||
|
|
||
| FP-Quant는 **매우 큰 배치(batch) 크기**에서 최고의 성능을 발휘합니다. |
Contributor
There was a problem hiding this comment.
Suggested change
| FP-Quant는 **매우 큰 배치(batch) 크기**에서 최고의 성능을 발휘합니다. | |
| 현재 FP-Quant는 매우 큰 배치(batch) 처리 상황에서 최고의 성능을 발휘합니다. |
제안드립니다!
skwh54
reviewed
Aug 8, 2025
| ) | ||
| ``` | ||
|
|
||
| [GPTQ](https://github.com/IST-DASLab/FP-Quant)를 통해 **사전 처리(Pre-processing)** 하여 더 높은 품질을 얻을 수도 있습니다. |
Contributor
There was a problem hiding this comment.
원문에는 FP Format Quantization Harness로 링크가 되어 있는데 GPTQ에 링크를 추가한 것은 의도하신 걸까요?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Translated the
fp_quant.mdfile of the documentation to Korean.Thank you in advance for your review.
Part of #20179
Before reviewing
[[lowercased-header]])Who can review? (Initial)
May you please review this PR?
@jungnerd, @luckyvickyricky, @chelsseeey, @amo33, @skwh54 , @D15M4S
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)