CsRic

CsRic's Stars

• deepseek-ai/open-infra-index

  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

  6.5k178

• deepseek-ai/DualPipe

  A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.

  Language:Python2.4k224

• deepseek-ai/DeepEP

  DeepEP: an efficient expert-parallel communication library

  Language:Cuda6.9k581

• deepseek-ai/FlashMLA

  FlashMLA: Efficient MLA decoding kernels

  Language:C++11.1k756

• MuhammadMoinFaisal/Pool-Shot-Predictor-with-OpenCV

  Pool Shot Predictor with OpenCV: Will the Ball Go Into the Pocket?

  Language:Python4

• Tokamak-USTC/ReSampler

  a simple and disk-free tool to help producers resample their sounds

  Language:C++3

• kvcache-ai/ktransformers

  A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

  Language:Python12.2k800

• IntQuant/noita_entangled_worlds

  True coop multiplayer mod for Noita.

  Language:Lua57934

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python11.6k2.6k

• 996icu/996.ICU

  Repo for counting stars and contributing. Press F to pay respect to glorious developers.

  270k21.1k

• deepseek-ai/DeepSeek-R1

  84.8k10.9k

• mandarine3ds/mandarine

  A Citra fork with new features and hacks which are experimental and may not be present upstream

  Language:C++57423

• HigherOrderCO/HVM

  A massively parallel, optimal functional runtime in Rust

  Language:Cuda10.9k419

• HigherOrderCO/Bend

  A massively parallel, high-level programming language

  Language:Rust18.4k457

• InternLM/InternEvo

  InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

  Language:Python35961

• vikhyat/moondream

  tiny vision language model

  Language:Python7.5k581

• SJTU-IPADS/PowerInfer

  High-speed Large Language Model Serving for Local Deployment

  Language:C++8.1k424

• gbevin/ShowMIDI

  Multi-platform GUI application to effortlessly visualize MIDI activity

  Language:C++68923

• state-spaces/mamba

  Mamba SSM architecture

  Language:Python14.1k1.2k

• kfrlib/kfr

  Fast, modern C++ DSP framework, FFT, Sample Rate Conversion, FIR/IIR/Biquad Filters (SSE, AVX, AVX-512, ARM NEON)

  Language:C++1.7k256

• iPlug2/iPlug2

  C++ Audio Plug-in Framework for desktop, mobile and web

  Language:C2k300

• UbiquitousLearning/mllm

  Fast Multimodal LLM on Mobile Devices

  Language:C++72383

• deepseek-ai/DeepSeek-V3

  Language:Python90.8k14.7k

• TruthOriginem/Starsector-Localization-CN

  Language:Java895

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda2.3k236

• Genymobile/scrcpy

  Display and control your Android device

  Language:C118k11.2k

• thunlp/Seq1F1B

  Sequence-level 1F1B schedule for LLMs.

  Language:Python161

• Hsword/SpotServe

  SpotServe: Serving Generative Large Language Models on Preemptible Instances

  1129

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python16.1k1.5k

• kvcache-ai/Mooncake

  Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

  Language:C++2.7k165