The Artifact of NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering

A large-scale simulation framework for LLM inference

Various HDL (Verilog) IP Cores

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Pin based tool for simulation of rack-scale disaggregated memory systems

OSDI'24 Nomad implementation

cricket is a virtualization solution for GPUs

Open source FPGA-based NIC and platform for in-network compute

Implement HNSW accelerator on FPGA for Approximate Nearest Neighbor Search

Latency and Memory Analysis of Transformer Models for Training and Inference

An energy-efficient RISC-V floating-point compute cluster.

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT4.0/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

example code for using DC QP for providing RDMA READ and WRITE operations to remote GPU memory

RISC-V SystemC-TLM simulator

SERV - The SErial RISC-V CPU

PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization

GLake: optimizing GPU memory management and IO transmission.

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

RoCE v2 hardware and software implementation

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

PsPIN: A RISC-V in-network accelerator for flexible high-performance low-power packet processing

Scalable Network Stack for FPGAs (TCP/IP, RoCEv2)

A DPDK repo with Corundum driver

leaked prompts of GPTs

corundum work on vu13p

Open source FPGA-based NIC and platform for in-network compute

Open Programmable Acceleration Engine

DeepSeek Coder: Let the Code Write Itself