Comments (2)
upgrade to the latest vllm v0.5.1. worked for me!
from vllm.
My first time ever using vLLM and it happens that I wanted to use it with phi-3, sure enough, same issue. Here is my repro too:
Python: 3.10
CUDA: 12.2
from vllm import SamplingParams, LLM
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="microsoft/Phi-3-mini-128k-instruct")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
Traceback (most recent call last):
File "/home/nevercast/vllm/vllm_run.py", line 11, in <module>
llm = LLM(model="microsoft/Phi-3-mini-128k-instruct")
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 144, in __init__
self.llm_engine = LLMEngine.from_engine_args(
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 336, in from_engine_args
engine_config = engine_args.create_engine_config()
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 630, in create_engine_config
model_config = ModelConfig(
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/vllm/config.py", line 137, in __init__
self.hf_config = get_config(self.model, trust_remote_code, revision,
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/vllm/transformers_utils/config.py", line 48, in get_config
raise e
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/vllm/transformers_utils/config.py", line 33, in get_config
config = AutoConfig.from_pretrained(
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 989, in from_pretrained
return config_class.from_dict(config_dict, **unused_kwargs)
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/transformers/configuration_utils.py", line 772, in from_dict
config = cls(**config_dict)
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/transformers/models/phi3/configuration_phi3.py", line 158, in __init__
self._rope_scaling_validation()
File "/home/nevercast/vllm/.venv/lib/python3.10/site-packages/transformers/models/phi3/configuration_phi3.py", line 185, in _rope_scaling_validation
raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}")
ValueError: `rope_scaling`'s type field must be one of ['su', 'yarn'], got longrope
from vllm.
Related Issues (20)
- [Doc]: massive amount of docs are missing - just empty pages HOT 1
- [Feature]: need to be able to load tiny models with vllm for testing - PagedAttention forces large models HOT 2
- [Bug]: Unable to generate output when add_eos_token = True for Mistral 7b instruct v0.1
- [Bug]: Unable to generate text tokens when add_eos_token = true for Mistral 7B instruct v0.1 HOT 1
- [Bug]: DeepSeek-Coder-V2-Instruct-AWQ assert self.quant_method is not None HOT 5
- [Usage]: Is there an option to reduce GPU memory usage? HOT 4
- [Bug]: Dockerfile Build breaks in local
- [Installation]: build docker images: Failed to build mamba-ssm
- [Bug]: pytest failure on kernels/test_cutlass.py test_cutlass_fp8_gemm
- [BUG] OpenAI server stalled after processing an embedding request while serving a chat model HOT 1
- [Model]: Does vllm currently support the Llama-3.1-405B-Instruct multimodal ? HOT 1
- [Bug]: Error in how HiddenStates are handled for speculative decoding
- [Usage]: Can the embedding model be deployed using the openai interface? HOT 2
- [Bug]: Docker.xpu build failed
- [Bug] : ROCM quantization check fail in version 0.5.4 for GPTQ and AWQ HOT 1
- [Bug]: error while attempting to bind on address ('0.0.0.0', 8000): address already in use HOT 3
- [Bug]: ImportError related to compressed tensors module HOT 1
- [Bug]: AutoAWQ marlin methods error HOT 6
- [Performance]: How to measure and understand the performance benefit of prefix caching HOT 2
- [Feature]: Context Parallelism HOT 4
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.