Comments (3)
@CharlesFauman Kaichao is a visiting student at UC Berkeley and a new member of the vLLM team. We talk and meet in person every week here at Berkeley. We asked @youkaichao to help us debug the long-lasting NCCL bugs in vLLM and we found out that it is caused by one specific new version of NCCL. Originally we would like to include NCCL in our wheel, but the pypi wheel size limit prevents us from doing this. We eventually have to ship nccl in another pypi package to get around this size limit.
If you don't like this new dependency (actually we don't like this dependency as well), please comment this issue to help us get a pypi limit increase.
from vllm.
Please download it yourself, and use VLLM_NCCL_SO_PATH
to point to the path. We have no choice before pypi/support#3792 .
from vllm.
this feels more deserving of a public discussion, for such a widely used open source repo
you can more easily hide malicious code in a github release than pypi. and you, a contributor with just 3 weeks of history contributing to this repo, have sole control over that distribution.
this situation feels quite sketchy.
from vllm.
Related Issues (20)
- [Bug]: RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
- [Speculative decoding]: The content generated by speculative decoding is inconsistent with the content generated by the target model HOT 3
- [Performance]: Is kv cache implemented globally in vllm, It can be shared by multiple concurrent inferences? HOT 1
- [Feature]: Make a unstable latest docker image
- [Performance]: gptq and awq quantization do not improve the performance HOT 2
- [Installation]: Compiling VLLM for cpu only. HOT 2
- [New Model]: mistralai/Codestral-22B-v0.1 HOT 3
- [Usage]: Streaming Response from vLLM 0.4.2 -> 0.4.3 HOT 2
- [Usage]: Function calling for mistral v0.3
- [Bug]: vLLM does not support virtual GPU
- [Bug]: Unexpected prompt token logprob behaviors of llama 2 when setting echo=True for openai-api server HOT 1
- [Bug]: Getting an empty string ('') for every call on fine-tuned Code-Llama-7b-hf model
- [Bug]: non-deterministic Python gc order leads to flaky tests HOT 13
- [Usage]: Howto quiet the terminal 'Info' outputs in vllm HOT 1
- [Performance]: [Automatic Prefix Caching] When hitting the KV cached blocks, the first execute is slow, and then is fast. HOT 1
- [Speculative decoding]: The content generated by speculative decoding is inconsistent with the content generated by : When I use the speculative mode and prompt_length+output_length > 2048, the error occurs HOT 1
- [Bug]: Qwen2 MoE: AttributeError: 'MergedColumnParallelLinear' object has no attribute 'weight'. Did you mean: 'qweight'? HOT 2
- [Bug]: with `--enable-prefix-caching` , `/completions` crashes server with `echo=True` above certain prompt length
- [RFC]: Refactor MoE
- [Bug]: TorchSDPAMetadata is out of date
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.