yangwang92 Goto Github PK

tas

TAS is a drop-in highly CPU efficient and scalable TCP acceleration service.

test

the-algorithm-ml

Source code for Twitter's Recommendation Algorithm

the-omega-project

Tools from Pugh et al.'s "Omega Project" for constraint-based compiler tools: The "Omega Library" for constraint manipulation; The "Omega Calculator" (text interface); the "Omega Test" for depedence analysis; the "Uniform Library" for code transformation; and the "Code generation" library for generating the transformed code. I am experimenting with tracking bugs with Lighthouse, but am not yet sure I've got it configure right --- see http://davew_haverford.lighthouseapp.com/projects/13658-the-omega-project/overview (if you can; if you can't, email [email protected]).

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

tiramisu

A polyhedral compiler for expressing fast and portable data parallel algorithms

tnoc

Network on Chip Implementation written in SytemVerilog

torch-blocksparse

Block-sparse primitives for PyTorch

torch-int

This repository contains integer operators on GPUs for PyTorch.

torchpq

Efficient implementations of Product Quantization and its variants using Pytorch and CUDA

torchscript-to-tvm

tpu

Reference models and tools for Cloud TPUs.

transformerengine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.

trema

Full-Stack OpenFlow Framework in Ruby

trex-stateless-gui

TRex stateless GUI

triton-dev

Development repository for the Triton language and compiler

tune

turingas

Assembler for NVIDIA Volta and Turing GPUs

tvm-mali

Optimizing Mobile Deep Learning on ARM GPU with TVM

tvm-models-baseline

tvm_gpu_gemm

play gemm with tvm

utvm_staticrt_codegen

This project contains a code generator that produces static C NN inference deployment code targeting tiny micro-controllers (TinyML) as replacement for other µTVM runtimes. This tools generates a runtime, which statically executes the compiled model. This reduces the overhead in terms of code size and execution time compared to having a dynamic on-device runtime.

vagrant

PISCES Simulation Environment

velox

A C++ vectorized database acceleration library aimed to optimizing query engines and data processing systems.

verigpu

OpenSource GPU, in Verilog, loosely based on RISC-V ISA

verilog-cam

Verilog Content Addressable Memory Module

vllm

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

vortex

vpp

Kubernetes network plugin based on the FD.io VPP

vq-diffusion