sammysun0711 / ov_llm_bench

Related projects ⓘ

Alternatives and complementary repositories for ov_llm_bench

• libxsmm / tpp-pytorch-extension
  Intel® Tensor Processing Primitives extension for Pytorch*
  ☆10Updated this week
• HabanaAI / DeepSpeed
  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
  ☆11Updated last month
• ROCm / pytorch-micro-benchmarking
  ☆16Updated this week
• openvinotoolkit / openvino_tokenizers
  OpenVINO Tokenizers extension
  ☆24Updated this week
• intel / intel-extension-for-openxla
  ☆39Updated last month
• intel / intel-extension-for-deepspeed
  Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note…
  ☆57Updated 2 months ago
• HabanaAI / hccl_demo
  ☆15Updated 2 months ago
• HabanaAI / Megatron-DeepSpeed
  Intel Gaudi's Megatron DeepSpeed Large Language Models for training
  ☆13Updated 3 weeks ago
• ROCm / TransformerEngine
  ☆12Updated this week
• intel / torch-ccl
  oneCCL Bindings for Pytorch*
  ☆86Updated 2 weeks ago
• intel / intel-xpu-backend-for-triton
  OpenAI Triton backend for Intel® GPUs
  ☆143Updated this week
• openvinotoolkit / openvino.genai
  Run Generative AI models with simple C++/Python API and using OpenVINO Runtime
  ☆145Updated this week
• intel / torch-xpu-ops
  ☆29Updated this week
• triton-inference-server / openvino_backend
  OpenVINO backend for Triton.
  ☆29Updated this week
• HabanaAI / Habana_Custom_Kernel
  Provides the examples to write and build Habana custom kernels using the HabanaTools
  ☆18Updated this week
• intel / xetla
  ☆59Updated this week
• ROCm / aotriton
  Ahead of Time (AOT) Triton Math Library
  ☆40Updated this week
• ROCm / triton
  Development repository for the Triton language and compiler
  ☆93Updated this week
• LLNL / HPAC
  ☆10Updated 3 months ago
• gpauloski / BERT-PyTorch
  BERT for Distributed PyTorch + AMP Training
  ☆12Updated last year
• ROCm / AITemplate
  AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…
  ☆11Updated 4 months ago
• north-numerical-computing / tensor-cores-numerical-behavior
  Test suite for probing the numerical behavior of NVIDIA tensor cores
  ☆30Updated 3 months ago
• ROCm / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆44Updated this week
• ROCm / apex
  A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
  ☆19Updated last week
• intel / xpumanager
  ☆93Updated last month
• mlcommons / logging
  MLPerf™ logging library
  ☆30Updated last week
• oneapi-src / oneAPI-tab
  oneAPI Technical Advisory Board (TAB) Meeting Notes
  ☆72Updated 9 months ago
• libxsmm / parlooper
  PArallelLOOPgEneratoR: Threaded Loops Code Generation Infrastructure targeting Tensor Contraction Applications such as GEMMs, Convolution…
  ☆18Updated last month
• OpenPPL / ppl.pmx
  ☆57Updated this week
• oneapi-src / level-zero-tests
  oneAPI Level Zero Conformance & Performance test content
  ☆46Updated this week