LocalAI/backend/python
fakezeta 3882130911
feat: Add Bitsandbytes quantization for transformer backend enhancement #1775 and fix: Transformer backend error on CUDA #1774 (#1823)
* fixes #1775 and #1774

Add BitsAndBytes Quantization and fixes embedding on CUDA devices

* Manage 4bit and 8 bit quantization

Manage different BitsAndBytes options with the quantization: parameter in yaml

* fix compilation errors on non CUDA environment
2024-03-14 23:06:30 +01:00
..
autogptq feat(autogpt/transformers): consume trust_remote_code (#1799) 2024-03-05 19:47:15 +01:00
bark Bump vLLM version + more options when loading models in vLLM (#1782) 2024-03-01 22:48:53 +01:00
common-env/transformers feat: Add Bitsandbytes quantization for transformer backend enhancement #1775 and fix: Transformer backend error on CUDA #1774 (#1823) 2024-03-14 23:06:30 +01:00
coqui Bump vLLM version + more options when loading models in vLLM (#1782) 2024-03-01 22:48:53 +01:00
diffusers feat(intel): add diffusers/transformers support (#1746) 2024-03-07 14:37:45 +01:00
exllama feat(intel): add diffusers/transformers support (#1746) 2024-03-07 14:37:45 +01:00
exllama2 feat(intel): add diffusers/transformers support (#1746) 2024-03-07 14:37:45 +01:00
mamba feat(intel): add diffusers/transformers support (#1746) 2024-03-07 14:37:45 +01:00
petals feat(intel): add diffusers/transformers support (#1746) 2024-03-07 14:37:45 +01:00
sentencetransformers Bump vLLM version + more options when loading models in vLLM (#1782) 2024-03-01 22:48:53 +01:00
transformers feat: Add Bitsandbytes quantization for transformer backend enhancement #1775 and fix: Transformer backend error on CUDA #1774 (#1823) 2024-03-14 23:06:30 +01:00
transformers-musicgen Bump vLLM version + more options when loading models in vLLM (#1782) 2024-03-01 22:48:53 +01:00
vall-e-x feat(intel): add diffusers/transformers support (#1746) 2024-03-07 14:37:45 +01:00
vllm Bump vLLM version + more options when loading models in vLLM (#1782) 2024-03-01 22:48:53 +01:00
README.md refactor: move backends into the backends directory (#1279) 2023-11-13 22:40:16 +01:00

Common commands about conda environment

Create a new empty conda environment

conda create --name <env-name> python=<your version> -y

conda create --name autogptq python=3.11 -y

To activate the environment

As of conda 4.4

conda activate autogptq

The conda version older than 4.4

source activate autogptq

Install the packages to your environment

Sometimes you need to install the packages from the conda-forge channel

By using conda

conda install <your-package-name>

conda install -c conda-forge <your package-name>

Or by using pip

pip install <your-package-name>