Pinned Repositories
nccl
Optimized primitives for collective multi-GPU communication
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.
compiler
mlir-nngo
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
shixuan94's Repositories
shixuan94/compiler
shixuan94/mlir-nngo
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure