Giter VIP home page Giter VIP logo

Comments (6)

grimoire avatar grimoire commented on June 1, 2024 1

可以去掉,因为 transformers 原来用来生成 token 映射的方式比较慢(两层循环遍历 token 组合),所以这里做个 cache 以免下次重复生成。可以删掉
还有 internlm 的 tp 似乎确实存在问题,正在排查中。

from lmdeploy.

lvhan028 avatar lvhan028 commented on June 1, 2024 1

profile_serving.py用的数据是:

wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json

from lmdeploy.

happened avatar happened commented on June 1, 2024

重新编译并且安装后 用python3 -m lmdeploy.serve.client {server_ip_addresss}:33337 internlm 测试了下 ,结果是正常的了

benchmark中关于profile_serving中测试集的dataset能提供一下嘛,看脚本里面对json格式是有要求的

另外profile_generation测试对应tp为2的workspace目录会coredump

image

from lmdeploy.

grimoire avatar grimoire commented on June 1, 2024

@lvhan028 profiling_serving 的 dataset 方面方便提供一些信息吗

coredump 的问题这边的环境上无法复现,能提供更详细的环境信息吗?

from lmdeploy.

happened avatar happened commented on June 1, 2024

具体步骤如下

#启动容器 宿主机当前为双T4机器
docker run -itd --net=host --name internlm_server
    --gpus all -v /data/work/deploy-interlm:/workspace 
 -v /data/models/:/models 
 --shm-size 16g 
 --cap-add=SYS_PTRACE --cap-add=SYS_ADMIN --security-opt seccomp=unconfined
 --env NCCL_LAUNCH_MODE=GROUP openmmlab/lmdeploy:latest bash


# 下载仓库并编译
git clone https://github.com/InternLM/lmdeploy.git
mkdir build && cd build 
bash ../generate.sh
make && make install

#转换模型为turbomind格式
python3 -m lmdeploy.serve.turbomind.deploy internlm-chat-7b /models/internlm-chat-7b hf  --tokenizer_path /models/internlm-chat-7b/tokenizer.model  --tp 2

#benchmark
cd /opt/tritonserver/lmdeploy
export PYTHONPATH=./:$PYTHONPATH
python3 benchmark/profile_generation.py --model_path /opt/tritonserver/lmdeploy/workspace --model_name internlm --concurrency 4 --input_seqlen 1 --output_seqlen 512--test_round 4

操作就是这样 这个会和拆分有关嘛

from lmdeploy.

grimoire avatar grimoire commented on June 1, 2024

不清楚,profile_generation 和 lmdeploy.turbomind.chat 用的接口类似,如果 chat 能加载成功的话 profile 应该也可以。

from lmdeploy.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.