Comments (2)
Hi, thanks for the interests in our work! It should theoretically support different LLM designs, but we need to implement the support (just a few lines of code). Please refer to awq/quantize/pre_quant.py
and awq/quantize/auto_scale.py
from llm-awq.
@tonylins Thanks.
When I install the efficient W4A16 CUDA kernel with python setup.py install
, it requires -std=c++14
instead of -std=c++17
to be set in setup.py
.
extra_compile_args = {
"cxx": ["-g", "-O3", "-fopenmp", "-lgomp", "-std=c++14"],
"nvcc": ["-O3", "-std=c++14", "-keep"],
}
However, it also failed with the errors when using -std=c++14
. Which Pytorch version do you use? Could you please give some advice?
/usr/local/anaconda3/envs/awq/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:58:59: error: invalid static_cast from type ‘const torch::OrderedDict<std::basic_string<char>, at::Tensor>’ to type ‘torch::OrderedDict<std::basic_string<char>, at::Tensor>&’
/usr/local/anaconda3/envs/awq/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:71:61: error: invalid static_cast from type ‘const torch::OrderedDict<std::basic_string<char>, std::shared_ptr<torch::nn::Module> >’ to type ‘torch::OrderedDict<std::basic_string<char>, std::shared_ptr<torch::nn::Module> >&’
The root cause maybe that a new gcc version (>5.4) is required. As for gcc 5.4.0, the issue can be solved by modifying the /usr/local/anaconda3/envs/awq/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h
.
copy->parameters_.size() == this -> parameters_.size()
copy->buffers_.size() == this -> buffers_.size()
copy->children_.size() == this -> children_.size()
from llm-awq.
Related Issues (20)
- reproduce Llama2 7b failure : RuntimeError: The expanded size of the tensor (4608) must match the existing size (4096) at non-singleton dimension 3. Target sizes: [65, 32, 512, 4608]. Tensor sizes: [65, 1, 512, 4096] HOT 3
- RuntimeError: Unknown Layout in CUDA Kernel Execution
- Use awq to quantize Deepseek-coder-33B-instruct model
- run_awq.<locals>.Catcher.forward() error
- KeyError: 'llava_llama' HOT 1
- Error while generating real quantized weights for VILA
- Weight int4 quantization, but actually it is int16 HOT 4
- Possible Bug in "_search_module_scale" Function
- AWQ for non-transformer layers?
- Out of memory in Jetson Orin NX 8GB
- Inquiry about Minimum GPU Requirements HOT 1
- when q-group-size = -1,the code will not run
- Weight Packing Format
- illegal memory access when input tokens < 8
- Grok-1 AWQ
- can awq support 3-bit,2-bit, 8-bit quantization? HOT 1
- awq_inference_engine is missing from source, so quantizing custom models fails HOT 2
- Support for Qwen models HOT 2
- AWQ for non-Transfomer Implementation HOT 3
- Error while Quantizing OWLv2 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 llm-awq.