KateBlueSky

cutlass-fork

CUDA Templates for Linear Algebra Subroutines

FlagGems

FlagGems is an operator library for large language models implemented in Triton Language.

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

lc0

SYCL work

llama.cpp

Port of Facebook's LLaMA model in C/C++

llvm

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

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.

triton

Development repository for the Triton language and compiler

vllm

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

xetla

KateBlueSky/intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

KateBlueSky/lc0

SYCL work

KateBlueSky/llama.cpp

Port of Facebook's LLaMA model in C/C++

KateBlueSky/llvm

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

KateBlueSky/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.

KateBlueSky/triton

Development repository for the Triton language and compiler

KateBlueSky/vllm

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

KateBlueSky/xetla