[docs] Redesign (#31757)
* toctree * not-doctested.txt * collapse sections * feedback * update * rewrite get started sections * fixes * fix * loading models * fix * customize models * share * fix link * contribute part 1 * contribute pt 2 * fix toctree * tokenization pt 1 * Add new model (#32615) * v1 - working version * fix * fix * fix * fix * rename to correct name * fix title * fixup * rename files * fix * add copied from on tests * rename to `FalconMamba` everywhere and fix bugs * fix quantization + accelerate * fix copies * add `torch.compile` support * fix tests * fix tests and add slow tests * copies on config * merge the latest changes * fix tests * add few lines about instruct * Apply suggestions from code review Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * fix * fix tests --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * "to be not" -> "not to be" (#32636) * "to be not" -> "not to be" * Update sam.md * Update trainer.py * Update modeling_utils.py * Update test_modeling_utils.py * Update test_modeling_utils.py * fix hfoption tag * tokenization pt. 2 * image processor * fix toctree * backbones * feature extractor * fix file name * processor * update not-doctested * update * make style * fix toctree * revision * make fixup * fix toctree * fix * make style * fix hfoption tag * pipeline * pipeline gradio * pipeline web server * add pipeline * fix toctree * not-doctested * prompting * llm optims * fix toctree * fixes * cache * text generation * fix * chat pipeline * chat stuff * xla * torch.compile * cpu inference * toctree * gpu inference * agents and tools * gguf/tiktoken * finetune * toctree * trainer * trainer pt 2 * optims * optimizers * accelerate * parallelism * fsdp * update * distributed cpu * hardware training * gpu training * gpu training 2 * peft * distrib debug * deepspeed 1 * deepspeed 2 * chat toctree * quant pt 1 * quant pt 2 * fix toctree * fix * fix * quant pt 3 * quant pt 4 * serialization * torchscript * scripts * tpu * review * model addition timeline * modular * more reviews * reviews * fix toctree * reviews reviews * continue reviews * more reviews * modular transformers * more review * zamba2 * fix * all frameworks * pytorch * supported model frameworks * flashattention * rm check_table * not-doctested.txt * rm check_support_list.py * feedback * updates/feedback * review * feedback * fix * update * feedback * updates * update --------- Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com> Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
This commit is contained in:
Steven Liu
@@ -16,32 +16,50 @@ rendered properly in your Markdown viewer.
|
||||
|
||||
# EETQ
|
||||
|
||||
The [EETQ](https://github.com/NetEase-FuXi/EETQ) library supports int8 per-channel weight-only quantization for NVIDIA GPUS. The high-performance GEMM and GEMV kernels are from FasterTransformer and TensorRT-LLM. It requires no calibration dataset and does not need to pre-quantize your model. Moreover, the accuracy degradation is negligible owing to the per-channel quantization.
|
||||
The [Easy & Efficient Quantization for Transformers (EETQ)](https://github.com/NetEase-FuXi/EETQ) library supports int8 weight-only per-channel quantization for NVIDIA GPUs. It uses high-performance GEMM and GEMV kernels from [FasterTransformer](https://github.com/NVIDIA/FasterTransformer) and [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM). The attention layer is optimized with [FlashAttention2](https://github.com/Dao-AILab/flash-attention). No calibration dataset is required, and the model doesn't need to be pre-quantized. Accuracy degradation is negligible owing to the per-channel quantization.
|
||||
|
||||
Make sure you have eetq installed from the [release page](https://github.com/NetEase-FuXi/EETQ/releases)
|
||||
```
|
||||
EETQ further supports fine-tuning with [PEFT](https://huggingface.co/docs/peft).
|
||||
|
||||
Install EETQ from the [release page](https://github.com/NetEase-FuXi/EETQ/releases) or [source code](https://github.com/NetEase-FuXi/EETQ). CUDA 11.4+ is required for EETQ.
|
||||
|
||||
<hfoptions id="install">
|
||||
<hfoption id="release page">
|
||||
|
||||
```bash
|
||||
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
|
||||
```
|
||||
or via the source code https://github.com/NetEase-FuXi/EETQ. EETQ requires CUDA capability <= 8.9 and >= 7.0
|
||||
```
|
||||
|
||||
</hfoption>
|
||||
<hfoption id="source code">
|
||||
|
||||
```bash
|
||||
git clone https://github.com/NetEase-FuXi/EETQ.git
|
||||
cd EETQ/
|
||||
git submodule update --init --recursive
|
||||
pip install .
|
||||
```
|
||||
|
||||
An unquantized model can be quantized via "from_pretrained".
|
||||
</hfoption>
|
||||
</hfoptions>
|
||||
|
||||
Quantize a model on-the-fly by defining the quantization data type in [`EetqConfig`].
|
||||
|
||||
```py
|
||||
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)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"meta-llama/Llama-3.1-8B",
|
||||
torch_dtype="auto",
|
||||
device_map="auto",
|
||||
quantization_config=quantization_config
|
||||
)
|
||||
```
|
||||
|
||||
A quantized model can be saved via "saved_pretrained" and be reused again via the "from_pretrained".
|
||||
Save the quantized model with [`~PreTrainedModel.save_pretrained`] so it can be reused again with [`~PreTrainedModel.from_pretrained`].
|
||||
|
||||
```py
|
||||
quant_path = "/path/to/save/quantized/model"
|
||||
model.save_pretrained(quant_path)
|
||||
model = AutoModelForCausalLM.from_pretrained(quant_path, device_map="auto")
|
||||
```
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user