Irvingwangjr

Irvingwangjr's Stars

• uber-go/automaxprocs

  Automatically set GOMAXPROCS to match Linux container CPU quota.

  Language:Go4k157

• alibaba/open-local

  cloud-native local storage management system for stateful workload, low-latency with simplicity

  Language:Go46481

• sgl-project/sglang

  SGLang is a fast serving framework for large language models and vision language models.

  Language:Python5.3k374

• intel/llm-on-ray

  Pretrain, finetune and serve LLMs on Intel platforms with Ray

  Language:Python9528

• Netflix/asgard

  [Asgard is deprecated at Netflix. We use Spinnaker ( www.spinnaker.io ).] Web interface for application deployments and cloud management in Amazon Web Services (AWS). Binary download: http://github.com/Netflix/asgard/releases

  Language:Groovy2.2k403

• NVIDIA/NeMo

  A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

  Language:Python11.6k2.4k

• v6d-io/v6d

  vineyard (v6d): an in-memory immutable data manager. (Project under CNCF, TAG-Storage)

  Language:C++827122

• NVIDIA/NeMo-Aligner

  Scalable toolkit for efficient model alignment

  Language:Python51657

• open-telemetry/opentelemetry-specification

  Specifications for OpenTelemetry

  Language:Makefile3.7k887

• InternLM/xtuner

  An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

  Language:Python3.8k302

• grpc/grpc-go

  The Go language implementation of gRPC. HTTP/2 based RPC

  Language:Go20.9k4.3k

• mindprince/gonvml

  NVIDIA Management Library (NVML) bindings for Go

  Language:C10746

• TUDB-Labs/mLoRA

  An Efficient "Factory" to Build Multiple LoRA Adapters

  Language:Python25339

• openkruise/rollouts

  Enhanced Rollouts features for application automation.

  Language:Go21867

• kudobuilder/kuttl

  KUbernetes Test TooL (kuttl)

  Language:Go66986

• punica-ai/punica

  Serving multiple LoRA finetuned LLM as one

  Language:Python95545

• cupy/cupy

  NumPy & SciPy for GPU

  Language:Python9.1k833

• NVIDIA-Merlin/HierarchicalKV

  HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of HierarchicalKV is to store key-value feature-embeddings on high-bandwidth memory (HBM) of GPUs and in host memory. It also can be used as a generic key-value storage.

  Language:Cuda12825

• google/tensorstore

  Library for reading and writing large multi-dimensional arrays.

  Language:C++1.3k120

• google/nsjail

  A lightweight process isolation tool that utilizes Linux namespaces, cgroups, rlimits and seccomp-bpf syscall filters, leveraging the Kafel BPF language for enhanced security.

  Language:C++2.9k275

• containers/nri-plugins

  A collection of community maintained NRI plugins

  Language:Go5424

• NVIDIA/cuda-checkpoint

  CUDA checkpoint and restore utility

  Language:Cuda1998

• efficient/rdma_bench

  A framework to understand RDMA

  Language:C368110

• kubernetes-csi/csi-driver-host-path

  A sample (non-production) CSI Driver that creates a local directory as a volume on a single node

  Language:Go317206

• facebookresearch/fairscale

  PyTorch extensions for high performance and large scale training.

  Language:Python3.2k277

• Plan9-Archive/plan9-4e

  Mirror of Plan 9 4th Edition from p9f

  Language:C123

• NVIDIA/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.

  Language:C++8.3k917

• msgpack/msgpack

  MessagePack is an extremely efficient object serialization library. It's like JSON, but very fast and small.

  7k518

• Tradias/asio-grpc

  Asynchronous gRPC with Asio/unified executors

  Language:C++35934

• intel/pcm

  Intel® Performance Counter Monitor (Intel® PCM)

  Language:C++2.7k469