Hugging Face's logo

TMElyralab
/
lyraChatGLM

English
LLM
ChatGLM6B
Model card Files Community
49
lyraChatGLM / README.md
vanewu's picture
vanewu
update todolist
1423815
preview code
|
raw
history blame
3.83 kB
metadata
license: creativeml-openrail-m
language:
  - en
tags:
  - LLM
  - tensorRT
  - ChatGLM

Model Card for lyraChatGLM

lyraChatGLM is currently the fastest ChatGLM-6B available. To the best of our knowledge, it is the first accelerated version of ChatGLM-6B.

The inference speed of lyraChatGLM has achieved 10x acceleration upon the ealry original version. We are still working hard to further improve the performance.

Among its main features are:

  • weights: original ChatGLM-6B weights released by THUDM.
  • device: lyraChatGLM is mainly based on TensorRT compiled for SM=80 (A100, for example).
  • batch_size: compiled with dynamic batch size, max batch_size = 8

Speed

test environment

  • device: Nvidia A100 40G
  • batch size: 8

Since early chatGLM version didn't suport batch inference, original in below table was measured on batch_size=1

According to this discussion, this bug has been fixed and the speed on batch_size=8 reachs up to 137 tokens/s. We will evaluate and update the latest performance.

version speed
original 30 tokens/s
lyraChatGLM 310 tokens/s

Model Sources

Try Demo in 2 fast steps 

#step 1
git clone https://huggingface.co/TMElyralab/lyraChatGLM
cd lyraChatGLM

#step 2
docker run --gpus=1 --rm --net=host -v ${PWD}:/workdir yibolu96/lyra-chatglm-env:0.0.1 python3 /workdir/demo.py

Uses 

from transformers import AutoTokenizer
from faster_chat_glm import GLM6B, FasterChatGLM


MAX_OUT_LEN = 100
tokenizer = AutoTokenizer.from_pretrained('./models', trust_remote_code=True)
input_str = ["为什么我们需要对深度学习模型加速？", ]
inputs = tokenizer(input_str, return_tensors="pt", padding=True)
input_ids = inputs.input_ids.to('cuda:0')


plan_path = './models/glm6b-bs8.ftm'
# kernel for chat model.
kernel = GLM6B(plan_path=plan_path,
               batch_size=1,
               num_beams=1,
               use_cache=True,
               num_heads=32,
               emb_size_per_heads=128,
               decoder_layers=28,
               vocab_size=150528,
               max_seq_len=MAX_OUT_LEN)

chat = FasterChatGLM(model_dir="./models", kernel=kernel).half().cuda()

# generate
sample_output = chat.generate(inputs=input_ids, max_length=MAX_OUT_LEN)
# de-tokenize model output to text
res = tokenizer.decode(sample_output[0], skip_special_tokens=True)
print(res)

Demo output

input

为什么我们需要对深度学习模型加速? 。

output

为什么我们需要对深度学习模型加速? 深度学习模型的训练需要大量计算资源,特别是在训练模型时,需要大量的内存、GPU(图形处理器)和其他计算资源。因此,训练深度学习模型需要一定的时间,并且如果模型不能快速训练,则可能会导致训练进度缓慢或无法训练。

以下是一些原因我们需要对深度学习模型加速:

  1. 训练深度神经网络需要大量的计算资源,特别是在训练深度神经网络时,需要更多的计算资源,因此需要更快的训练速度。

TODO：

We have implemented some special operators in ChatGLM, such as 2D rotary embedding, alpha residual, etcs.

We plan to add these operators on top of FasterTransformer to release a faster version.

Citation 

@Misc{lyraChatGLM2023,
  author =       {Kangjian Wu, Zhengtao Wang, Yibo Lu, Bin Wu},
  title =        {lyraChatGLM: Accelerating ChatGLM by 10x+},
  howpublished = {\url{https://huggingface.co/TMElyralab/lyraChatGLM}},
  year =         {2023}
}

Report bug