Comments (6)
cliffwoolley
commented on June 24, 2024
1
Please see NVIDIA/nvidia-container-toolkit#520 .
from vllm.
HelloCard
commented on June 24, 2024
wsl以及cudaGetDeviceCount错误……我遇到过一个类似的故障，原因是wsl外面安装了向日葵远程工具，向日葵创建的虚拟显卡干扰了wsl里面的vllm。
from vllm.
gaye746560359
commented on June 24, 2024
wsl以及cudaGetDeviceCount错误……我遇到过一个类似的故障，原因是wsl外面安装了向日葵远程工具，向日葵创建的虚拟显卡干扰了wsl里面的vllm。
我卸载了向日葵，运行还是报错
from vllm.
MarioLiebisch
commented on June 24, 2024
Stumbled over this issue while looking around to see if there have been any fixes.
I just checked the Nvidia driver feedback thread and it's actually a listed known issue:
PyTorch-CUDA Docker not compatible with CUDA 12.5/GRD 555.85 [4668302]
from vllm.
gaye746560359
commented on June 24, 2024
Docker Desktop 时遇到此症状，则表示正在修复（升级捆绑的 nvidia-container-toolkit）；预计什么时候修复更新？
from vllm.
cliffwoolley
commented on June 24, 2024
Docker Desktop 时遇到此症状，则表示正在修复（升级捆绑的 nvidia-container-toolkit）；预计什么时候修复更新？
We are moving as quickly with it as we can, but I don't have an ETA yet, which is why I didn't list one in the other issue.
from vllm.
Related Issues (20)
- [Bug]: LLM.generate() collapse with some padding side HOT 1
- [Performance]: Speculative Performance almost same or lower HOT 4
- [Bug]: Tokenizer setter of LLM without CachedTokenizer adapter HOT 1
- [Usage]: Running Phi-3-small-128k-instruct with v0.4.3 without --trust-remote-code HOT 2
- [Feature]: support Classifier-Free Guidance Logits processor
- how to compile with GLIBCXX_USE_CXX11_ABI=1 HOT 2
- [Misc]: vllm ONLY allocate KVCache on the first device in CUDA_VISIBLE_DEVICES HOT 1
- [Misc]: Why prometheus metric vllm:request_success_total doubles the value? HOT 4
- [Bug]: prompt_logprobs doesn't work with openai compatible server HOT 11
- [Usage]:how to get the output embedding for a text generation model using vllm
- [Bug]: Pending but Avg generation throughput: 0.0 tokens/s HOT 1
- vllm推理THUDM/chatglm3-6b-128k 无法stop HOT 2
- [Usage]: How to load a model with less CPU memory
- [Bug]: a bug HOT 1
- [Bug]: When I call the speculative model through the vllm interface, an error is reported: TypeError: 'type' object is not subscriptable HOT 2
- [Bug]: chatglm3 with lora adapter HOT 3
- [Bug]: high gpu_memory_utilization with 'OOM' and low gpu_memory_utilization with 'No available memory for the cache blocks' HOT 1
- [Bug]: Regression in predictions in v0.4.3 HOT 4
- [Usage]: the docker image v0.4.3 cannot work HOT 5
- [Bug] [Speculative Decoding/flash_attn]: Flash attn backend crashes in speculative decoding 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.