cli99 Goto Github PK

llm-analysis

Latency and Memory Analysis of Transformer Models for Training and Inference

llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

megablocks

megatron-lm

Ongoing research training transformer language models at scale, including: BERT & GPT-2

minbert-assignment

Minimalist BERT implementation assignment for CS11-711

mingpt

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

mpipe

Python API for writing multiprocessing pipelines

project_openai_codex

python-mastery

Advanced Python Mastery (course by @dabeaz)

sagemaker-debugger

Amazon SageMaker Debugger provides functionality to save tensors during training of machine learning jobs and analyze those tensors

smdebug_examples

smoothquant

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

starter-academic

superbenchmark

A validation and profiling tool for AI infrastructure

telegram_forwarder

Forward message automatically from channel/group with telegram bot @/heroku

tensorrt

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

tlcbench

Benchmark scripts for TVM

torchview

torchview: visualize pytorch models

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

transformer_framework

framework for plug and play of various transformers (vision and nlp) with FSDP

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs