There are 1 repository under int8 topic.
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Reimplement RetinaFace use C++ and TensorRT
An innovative library for efficient LLM inference via low-bit quantization
a simple pipline of int8 quantization based on tensorrt.
NCNN+Int8+YOLOv4 quantitative modeling and real-time inference
TensorRT Int8 Python version sample. TensorRT Int8 Python 实现例子。TensorRT Int8 Pythonの例です
A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.
LLM-Lora-PEFT_accumulate explores optimizations for Large Language Models (LLMs) using PEFT, LORA, and QLORA. Contribute experiments and implementations to enhance LLM efficiency. Join discussions and push the boundaries of LLM optimization. Let's make LLMs more efficient together!
quantization example for pqt & qat
IBO stands for "Internal binary operations" and it is a library for Java to read, write, and handle binary files and data types that aren't available in Java.
Int8Array.
8-bit signed integer mathematical constants.
Minimum signed 8-bit integer.
Test if a value is an Int8Array.
Maximum signed 8-bit integer.
Size (in bytes) of an 8-bit signed integer.
Convert a Node-API value to a signed 8-bit integer array.
Convert a Node-API value representing a strided array to a signed 8-bit integer array.
mxnet GluonCV quantization binary ternary models
Practicing C data types using the sizeof function
development quantization framework