Comments (5)
Could you do a bisection of the commits between 0.4.0 and 0.4.1 to pinpoint which is the commit that caused the issue? There is a possibility that this is fixed by #4463, but if it isn't, knowing the exact commit will help us to figure out what is going on :)
from vllm.
Could you do a bisection of the commits between 0.4.0 and 0.4.1 to pinpoint which is the commit that caused the issue? There is a possibility that this is fixed by #4463, but if it isn't, knowing the exact commit will help us to figure out what is going on :)
hi i will do pinpoint later. there is another infomation.
my launch cmd is
python3 -m vllm.entrypoints.openai.api_server --port 8000 --model /models/mixtral-8x7b/ --tensor-parallel-size 8 --max-num-batched-toke
ns 32768 --max-model-len 8192 --gpu-memory-utilization 0.9 --dtype float16
but if --dtype float16 change to --dtype float32 , inference result is fine.
from vllm.
Could you do a bisection of the commits between 0.4.0 and 0.4.1 to pinpoint which is the commit that caused the issue? There is a possibility that this is fixed by #4463, but if it isn't, knowing the exact commit will help us to figure out what is going on :)
and i tested #4463 #4517 , didnt work.
from vllm.
Could you do a bisection of the commits between 0.4.0 and 0.4.1 to pinpoint which is the commit that caused the issue? There is a possibility that this is fixed by #4463, but if it isn't, knowing the exact commit will help us to figure out what is going on :)
#3805 is the commit causes the issue.
from vllm.
further experiment shows it happens on pytorch version > 2.1.2
from vllm.
Related Issues (20)
- [Usage]: how should I do data parallelism using vLLM?
- [Bug]: torch.cuda.OutOfMemoryError: CUDA out of memory when Handle inference requests
- [Misc]: Should inference with temperature 0 generate the same results for a lora adapter and equivalent merged model? HOT 5
- [Bug]: CUDA illegal memory access when calling flash_attn_cuda.fwd_kvcache
- [Bug]: The openai deployment model takes twice as long to deploy as fastapi's approach to offline inference. HOT 1
- [Feature]: Linear adapter support for Mixtral
- [Feature]: VLLM suport for function calling in Mistral-7B-Instruct-v0.3 HOT 1
- [Bug]: Issue with Token Processing Efficiency and Key-Value Cache Utilization in AsyncLLMEngine
- [Bug]: WSL2(Including Docker) 2 GPU problem --tensor-parallel-size 2 HOT 1
- [Bug]: Unable to Use Prefix Caching in AsyncLLMEngine HOT 10
- [Performance]: What can we learn from OctoAI HOT 3
- [Bug]: Model Launch Hangs with 16+ Ranks in vLLM HOT 1
- [Usage]: Prefix caching in VLLM HOT 1
- [Bug]: Incorrect Example for the Inference with Prefix
- [Feature]: BERT models for embeddings HOT 1
- [Bug]: The Offline Inference Embedding Example Fails HOT 5
- [Bug]: Offline Inference with the OpenAI Batch file format yields unnecessary `asyncio.exceptions.CancelledError` HOT 2
- [Feature]: MoE kernels (Mixtral-8x22B-Instruct-v0.1) are not yet supported on CPU only ?
- [Bug]: vLLM api_server.py when using with prompt_token_ids causes error.
- [Bug]: loading squeezellm model
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.