Comments (4)
Hi @qwopqwop200 ! How's your day? 😄
I would like to extend an official invitation for you to join this project and being the maintainer and first-class reviwer on any commits to quantization codes. I believe your expertise will help this project grow more quickly and continue to make important contributions to the community.
Meanwhile, I will continue to extend and optimize this project on the following aspects:
- More faster speed on the execution of model quantization program and more controllable of RAM and VRAM usage.
- Support model offloading so that this project can be used in larger models on consumer level devices.
- An inference engine module that support multi-device and model parallelism inference and compatible with asgi frameworks such as FastAPI.
- An trainer that can fine-tune quantized model on down-stream tasks. (I think this is impossable without your help).
- And more others that community demanded and meaningful.
It would be my great honor to have you join in!
Looking forward to your reply! ❤️
from autogptq.
I think this project is very promising. I am thinking of participating in this project.
from autogptq.
Awesome!! What a great job 🎉
I'm also in a progress to learn how to integrate with triton and try to make it compatible with CUDA version in current codes, anyway, I will add your project to README.md and let anyone else to know there is a faster version of AutoGPTQ.
from autogptq.
Can't wait to cooperate with you! 🥂
from autogptq.
Related Issues (20)
- Why doesn't AutoGPTQ quantize lm_head layer? HOT 5
- What magnitude of avg loss indicates a relatively good result for a quantization model HOT 6
- Why LLaMA3-8B after GPTQ test in wikitext2 so bad? HOT 8
- [PR Ready for Review] [FEATURE] Extend Support for Phi-3
- [FEATURE] Backport vllm expanded Marlin kernel to autogptq. HOT 1
- [DEPRECATION] Discussion on Fused attention and QiGEN HOT 5
- Llama-3 8B Instruct quantized to 8 Bit spits out gibberish in transformers `model.generate()` but works fine in vLLM? HOT 5
- [BUG]safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
- [Question] Differences in quantization logic compared to AWQ
- [FEATURE] ADD SUPPORT DeepSeek-V2
- [BUG] ARM installation error
- [BUG] ROCm installation and building broken
- Target modules [] not found in the base model. Please check the target modules and try again.
- [BUG] Cannot install from source
- [BUG] Following the quant_with_alpaca.py example but keep getting "You shouldn't move a model that is dispatched using accelerate hooks." and the model is never saved.
- [FEATURE] Models that support MOE do GPTQ
- [FEATURE] Add marlin24 support
- How to select between different kernels?
- Question about data shape difference between quantization and forward
- [FEATURE] Added code support to 5,6,7 bits quantization can you please add me as contributor I will create a new pull request 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 autogptq.