MeeCreeps

MeeCreeps's Stars

• RWKV/rwkv.cpp

  INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

  Language:C++1.4k93

• AmberLJC/LLMSys-PaperList

  Large Language Model (LLM) Systems Paper List

  57524

• microsoft/ArchProbe

  A profiler to disclose and quantify hardware features on GPUs.

  Language:C++15822

• google/uVkCompute

  A micro Vulkan compute pipeline and a collection of benchmarking compute shaders

  Language:C++21736

• microsoft/T-MAC

  Low-bit LLM inference on CPU with lookup table

  Language:C++43932

• pytorch/torchchat

  Run PyTorch LLMs locally on servers, desktop and mobile

  Language:Python3.1k193

• tpoisonooo/how-to-optimize-gemm

  row-major matmul optimization

  Language:C++58478

• flame/how-to-optimize-gemm

  Language:C1.7k351

• google/spirv-tutor

  Language:Shell508

• SaschaWillems/VulkanCapsViewer

  Vulkan hardware capability viewer

  Language:C++31266

• mit-han-lab/qserve

  QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

  Language:Python40118

• mlc-ai/mlc-llm

  Universal LLM Deployment Engine with ML Compilation

  Language:Python18.7k1.5k

• Mozilla-Ocho/llamafile

  Distribute and run LLMs with a single file.

  Language:C++19k971

• johnma2006/mamba-minimal

  Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

  Language:Python2.5k185

• Syllo/nvtop

  GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

  Language:C8k291

• FMInference/DejaVu

  Language:Python26932

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python13.4k1.2k

• NVIDIA/FasterTransformer

  Transformer related optimization, including BERT, GPT

  Language:C++5.8k882

• SJTU-IPADS/PowerInfer

  High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

  Language:C++7.9k403

• lutzroeder/netron

  Visualizer for neural network, deep learning and machine learning models

  Language:JavaScript27.6k2.7k

• edufgf/CodeOptimizationTechniques

  Implementation and benchmark of optimization techniques and algorithms applied to the Matrix Multiplication problem on a CPU/GPU multithreaded environment.

  Language:C++81

• flame/blislab

  BLISlab: A Sandbox for Optimizing GEMM

  Language:C46799

• ggerganov/ggml

  Tensor library for machine learning

  Language:C++10.9k1k

• alibaba/MNN

  MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

  Language:C++8.6k1.7k

• facebookresearch/seamless_communication

  Foundational Models for State-of-the-Art Speech and Text Translation

  Language:Jupyter Notebook10.8k1.1k

• pytorch-labs/gpt-fast

  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

  Language:Python5.5k504

• flowtyone/flowty-realtime-lcm-canvas

  A realtime sketch to image demo using LCM and the gradio library.

  Language:Python1.8k149

• CNugteren/CLBlast

  Tuned OpenCL BLAS

  Language:C++1k205

• ermig1979/Simd

  C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, VMX(Altivec) and VSX(Power7) for PowerPC, NEON for ARM.

  Language:C++2k407

• chenzomi12/AISystem

  AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

  Language:Jupyter Notebook10.4k1.5k