Comments (2)
andyli386
commented on May 24, 2024
I get the same error with alpindale/c4ai-command-r-plus-GPTQ when I use openai api. But the first one or two request will get normal response.
from vllm.
hmellor
commented on May 24, 2024
I receive the error "Conversation roles must alternate user/assistant/user/assistant/..."
This shows that the original template is working as intended and that you aren't sending it messages in the format it expects.
prompt: '/opt/chattemplates/commandrplus.jinja'
This part of the log indicates that you're somehow passing the chat template path in as your prompt.
I'm closing this because it's user error, not a bug.
from vllm.
Related Issues (20)
- [Feature]: Add prompt token ids into logit processor? HOT 1
- [Bug]: speculative decoding got `shape mismatch` error with n>1 and random sample
- text_generation_router::infer: router/src/infer.rs:130: no permits available
- [Usage]: How to reload model when tensor_parallel_size > 1 ? HOT 2
- [Bug]: run vllm api with docker
- [Feature]: Support for MiniCPM-Llama3-V-2_5 the Multi-modal LLM
- [Bug]: Error executing method load_model. This might cause deadlock in distributed execution.
- [Feature]: pre release or nightly builds
- [Installation]: Reduce Image size when installing wheel with cuda 11.8 HOT 1
- [New Model]: Phi-3-medium-128k-instruct support HOT 1
- [Feature]: automatically select distributed inference backend HOT 2
- [Feature]: Support loading of sharded vLLM serialized models with Tensorizer HOT 4
- [Feature]: microsoft/Phi-3-vision-128k-instruct Vision support HOT 1
- [FastAPI related] Built an API, ended into torch.cuda.OutOfMemoryError: CUDA out of memory
- [Installation]: editable install fails with setuptools 70.0.0 HOT 3
- [Misc]: How to get the string value of token in the output of logprobs? HOT 3
- [Usage]: vllm inferring gemma7B is still very slow HOT 1
- [Bug]: vllm with gemma7b still slow HOT 1
- [Feature]: support `stream_options` option
- [Feature]: Please optimize the output print info about time count. 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.