-
gptq
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Oobabooga isn't a wrapper for llama.cpp, but it can act as such. A usual Oobabooga installation on windows will use a GPTQ wheel (binary) compiled for cuda/windows, or alternatively use llama.cpp's API and act as a GUI. On Linux you had the choice to use the triton or cuda branch for GPTQ, but I don't know if that is still the case. You can also go the route to use virtualized and hardware accelerated WSL2 Ubuntu on Windows and use anything similar to linux. See my guide
GPTQ is another quantization method, that works only for transformer model architectures. It quantizes the stored model weights in a non-linear fashion, and ends up having better quality compared to just linear quantization into a smaller data type. GPTQ has a triton and a cuda branch, which was tricky initially, as it lead to a lot of confusion and non-compatibility especially on windows.