Comments (5)
kir1to00
commented on May 27, 2024
1
和我很像啊，我也是win10，双卡2080ti，z170ar主板，安装并启用nvlink。不过我在wsl2里安装了最新版本的vllm以后一切正常。
@HelloCard 用了tensor-parallel-size参数吗？
用了tensor-parallel-size 2，运行了BagelMIsteryTour-v2-8x7B-AWQ、Qwen1.5-32B-Chat-AWQ、DaringMaid-20B-AWQ、orca-2-13B-AWQ
已经解决拉 @HelloCard
from vllm.
HelloCard
commented on May 27, 2024
和我很像啊，我也是win10，双卡2080ti，z170ar主板，安装并启用nvlink。不过我在wsl2里安装了最新版本的vllm以后一切正常。
from vllm.
kir1to00
commented on May 27, 2024
和我很像啊，我也是win10，双卡2080ti，z170ar主板，安装并启用nvlink。不过我在wsl2里安装了最新版本的vllm以后一切正常。
@HelloCard 用了tensor-parallel-size参数吗？
from vllm.
kir1to00
commented on May 27, 2024
使用nvidia-nccl-cu12==2.19.3 vllm=0.4.0.post1 成功启动
from vllm.
HelloCard
commented on May 27, 2024
和我很像啊，我也是win10，双卡2080ti，z170ar主板，安装并启用nvlink。不过我在wsl2里安装了最新版本的vllm以后一切正常。
@HelloCard 用了tensor-parallel-size参数吗？
用了tensor-parallel-size 2，运行了BagelMIsteryTour-v2-8x7B-AWQ、Qwen1.5-32B-Chat-AWQ、DaringMaid-20B-AWQ、orca-2-13B-AWQ
from vllm.
Related Issues (20)
- [Bug]: Qwen1.5-72B L20x8 latest vLLM TPOT slower than v0.4.0.post, 48ms vs 39ms, why? HOT 7
- [Usage]: How to determine how many concurrent requests can be supported in an acceptable time duration with demo api server? HOT 1
- [Feature]: how to make vllm to the model, which not in the support list HOT 2
- [Doc]: can't fing serving_embedding.py HOT 2
- [Bug]: No CUDA GPUs are available on 'CPU' use HOT 1
- [Feature]: add local_files_only parameter HOT 3
- [Doc]: Why is the PA kernel time cost in the decode phase optimized after turning on Prefix Caching? HOT 2
- [Misc]: a question about chunked-prefill in flash-attn backends HOT 1
- [Usage]: distributed inference with kuberay HOT 3
- [Feature]: Health check for restart policy HOT 1
- [Bug]: Shape error encountered in speculative decoding when `enable_lora=True`
- [RFC]: Add control panel support for vLLM HOT 3
- [Bug]: single lora request error make all processing requests error
- [Usage]: gpu memory usage when using tensor parallel HOT 1
- [Installation]: Do we have the plan to update the pip package installation method for the CPU backend.
- [Usage]: why can't I set gpu nums while use "tensor_parallel_size"?
- [Bug]: assert parts[0] == "base_model" AssertionError HOT 2
- [Bug]: Too strict version requirement on `tiktoken` HOT 3
- [Bug]: `CohereForAI/c4ai-command-r-v01`OSError: [Errno 12] Cannot allocate memory HOT 1
- [Misc]: When is the planned date for the next release? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vllm.