Comments (1)
We are happy to help, but you need to clarify more what you are seeing because I cannot follow the abve well
It is most useful if you can show:
- launch commands
- client request commands
- expected result
- actual result
from vllm.
Related Issues (20)
- [Feature]: Dockerfile.cpu for aarch64 HOT 1
- [Bug]: num_scheduler_steps > 1, n > 1 raise error
- [Usage]: vllm Docker: OSError: Incorrect path_or_model_id HOT 5
- [New Model]: Support for Idefics3 8B Llama3
- [Bug]: how to set gpu id in code? HOT 3
- [Usage]: How to call my custom agent through vllm's api service HOT 1
- [Bug]: AssertionError when using automatic prefix caching and prompt_logprobs HOT 1
- [Usage]: Distributed inference with edge case: model fits multiple GPUs, but number of GPUs cannot divide the model size evenly HOT 7
- [New Model]: Reflection-Llama-3.1-70B HOT 2
- [Bug]: vllm: error: unrecognized arguments: --config HOT 6
- [Bug]: --Chunked prefill can't be used together with num-scheduler-steps HOT 1
- [Bug]: RuntimeError: shape mismatch: value tensor of shape [3328, 7168] cannot be broadcast to indexing result of shape [3328] for OpenGVLab/InternVL2-40B HOT 2
- [Usage]: multi image inference for "OpenGVLab/InternVL2-8B" not working HOT 4
- [Usage]: How to access mlp layer using the current version vllm(0.4.0)
- [RFC]: More functionality for API control
- [Feature]: Reflection-Llama-3.1-70B tool-choice support HOT 2
- [Bug]: Qwen2-VL AssertionError: assert "factor" in rope_scaling. HOT 2
- [Usage]: How can i user scheduler with OpenAI Compatible Server HOT 5
- [Bug]: deepseek_v2 236B on 8XA100 wrong output vllm==0.5.4 HOT 5
- [Usage]: Throughput and quality issue with vllm 0.6.0. HOT 3
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.