06f1fd69a6
Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
2.4 KiB
2.4 KiB
EETQ eetq
EETQ 라이브러리는 NVIDIA GPU에 대해 int8 채널별(per-channel) 가중치 전용 양자화(weight-only quantization)을 지원합니다. 고성능 GEMM 및 GEMV 커널은 FasterTransformer 및 TensorRT-LLM에서 가져왔습니다. 교정(calibration) 데이터셋이 필요 없으며, 모델을 사전에 양자화할 필요도 없습니다. 또한, 채널별 양자화(per-channel quantization) 덕분에 정확도 저하가 미미합니다.
릴리스 페이지에서 eetq를 설치했는지 확인하세요.
pip install --no-cache-dir https://github.com/NetEase-FuXi/EETQ/releases/download/v1.0.0/EETQ-1.0.0+cu121+torch2.1.2-cp310-cp310-linux_x86_64.whl
또는 소스 코드 https://github.com/NetEase-FuXi/EETQ 에서 설치할 수 있습니다. EETQ는 CUDA 기능이 8.9 이하이고 7.0 이상이어야 합니다.
git clone https://github.com/NetEase-FuXi/EETQ.git
cd EETQ/
git submodule update --init --recursive
pip install .
비양자화 모델은 "from_pretrained"를 통해 양자화할 수 있습니다.
from transformers import AutoModelForCausalLM, EetqConfig
path = "/path/to/model".
quantization_config = EetqConfig("int8")
model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", quantization_config=quantization_config)
양자화된 모델은 "save_pretrained"를 통해 저장할 수 있으며, "from_pretrained"를 통해 다시 사용할 수 있습니다.
quant_path = "/path/to/save/quantized/model"
model.save_pretrained(quant_path)
model = AutoModelForCausalLM.from_pretrained(quant_path, device_map="auto")