A QUIC implementation in pure go

Transformers 3rd Edition

Reference implementation of Mistral AI 7B v0.1 model.

Inference code for Llama models

ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale

Attention is all you need implementation

Optimized primitives for collective multi-GPU communication

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

The figures of llama2 chakra traces

🧠 A study guide to learn about Transformers

Using OMNeT++ for Infiniband Network data flow mechanism simulation, performance & bottleneck exploration, specifically for distributed machine-learning systems in data center

Helios Traces from SenseTime

Data Center Traffic Generator Library

Deep Learning introduction and its application in various fields

QUIC and HTTP/3 implementation in Python

A DASH segment size aware rate adaptation model for DASH

RTSP/RTP/RTMP/FLV/HLS/MPEG-TS/MPEG-PS/MPEG-DASH/MP4/fMP4

Implementation of a RTP server that sends video stream (H.264/HEVC) using the Real-time Transport Protocol(RTP) based on Linux/MacOS. 一个基于Linux/MacOS平台的可以发送携带H.264/HEVC媒体类型的RTP视频流的示例程序。

Python Multicast Test Tool (Python2/3)

RTSP server based on GStreamer

Implementation of a streaming video server and client that communicate using the Real-Time Streaming Protocol (RTSP) and send data using the Realtime Transfer Protocol (RTP)

NS3 simulator for RDMA over Converged Ethernet v2 (RoCEv2), including the implementation of DCQCN, TIMELY, PFC, ECN and shared buffer switch

QUIC protocol implementation in python

Rtmp with Quic based transport medium