Pinned Repositories
Atom
Codebase for Atom
AURIN_API_Example
show how to use aurin api
AutoAWQ
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
basecaller
bert
TensorFlow code and pre-trained models for BERT
bignum
COMP90041-project
introduce to JAVA programming
Comp90054-pacman
pytorch_ddp_examples
pytorch_extension_examples
MrDoghead's Repositories
MrDoghead/COMP90041-project
introduce to JAVA programming
MrDoghead/Atom
Codebase for Atom
MrDoghead/AURIN_API_Example
show how to use aurin api
MrDoghead/AutoAWQ
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
MrDoghead/basecaller
MrDoghead/bignum
MrDoghead/brain-commonsense
MAST90109 project code
MrDoghead/COMP90024_2020_Project_G39_City_Analytics_on_the_Cloud
teamwork
MrDoghead/dlrm
MrDoghead/Link_prediction
2020-sml-project
MrDoghead/nmt-nemo
tenserRT neural machine translation
MrDoghead/pytorch_ddp_examples
MrDoghead/pytorch_extension_examples
MrDoghead/Chinese-LLaMA-Alpaca-2
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
MrDoghead/COMP90042NLP
subject materials
MrDoghead/crawler_sample
demos
MrDoghead/dien_tf2
MrDoghead/documentation
MrDoghead/export_llm_to_onnx
export llama to onnx
MrDoghead/FasterTransformer
Transformer related optimization, including BERT, GPT
MrDoghead/ffts
implementations of fft-like transformations
MrDoghead/GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
MrDoghead/LLM-FP4
The official implementation of the EMNLP 2023 paper LLM-FP4
MrDoghead/LLM-QAT
Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"
MrDoghead/mrdoghead.github.io
MrDoghead/nmt-onmt
MrDoghead/opennmt-py
Version 1.0
MrDoghead/spectral_clustering
includes power method
MrDoghead/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
MrDoghead/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs