Comments (2)
I've identified that the error happens exactly in the lora library at this setattr
line:
When setattr(parent, child_name, new_module)
is executed, and parent is a tensor parallel wrapper, child_name is a string "tp_wrapped_module", new_module is a lora linear layer.
from tensor_parallel.
I think I fixed it.
from tensor_parallel.
Related Issues (20)
- tensor_parallel method distributed=True HOT 2
- distributed TP model forward output's requires_grad is False HOT 5
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
- 2x slowdown using TP
- Would it suitable for the multi-GPU parallel inference for llama2?
- Support of 8-bit and 4-bit quantization HOT 1
- Segmentation fault (core dumped)
- RuntimeError: NCCL Error 3: internal error HOT 1
- ValueError: Model parameters were moved to incorrect devices, did call on model.cuda() or model.to(device)? If so, please avoid doing that
- AttributeError: object has no attribute 'devices'
- Out of GPU memory for two A10 GPUs HOT 1
- How to use the model in a scenario where it is stored in the Safetenors format?
- No output when using tensor_parallel HOT 1
- TensorParallel object has no attribute save_pretrained
- No implement of generate() when using models from hugging face.
- Can I use tensor_parallel to inference for a GPTQ quantized model?
- Now, does tensor_parallel no longer support the huggingface trainer?
- tensor_parallel int4 LLM is not working since release v2.0.0
- Customized generate func support?
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 tensor_parallel.