Alternatives and similar repositories for mmapeak

Users that are interested in mmapeak are comparing it to the libraries listed below

• Cornell-RelaxML / qtip
  ☆139Updated 3 weeks ago
• aikitoria / open-gpu-kernel-modules
  NVIDIA Linux open GPU with P2P support
  ☆25Updated last month
• mag- / gpu_benchmark
  Gpu benchmark
  ☆63Updated 5 months ago
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆177Updated this week
• KONAKONA666 / q8_kernels
  ☆71Updated 6 months ago
• LeanModels / DFloat11
  DFloat11: Lossless LLM Compression for Efficient GPU Inference
  ☆446Updated last month
• BlinkDL / fast.c
  Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.
  ☆72Updated 5 months ago
• chu-tianxiang / llama-cpp-torch
  llama.cpp to PyTorch Converter
  ☆33Updated last year
• Repeerc / flash-attention-v2-RDNA3-minimal
  a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA en…
  ☆43Updated 10 months ago
• leafspark / AutoGGUF
  automatically quant GGUF models
  ☆187Updated this week
• IST-DASLab / Quartet
  ☆71Updated 2 weeks ago
• IST-DASLab / qmoe
  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
  ☆277Updated last year
• ScalingIntelligence / good-kernels
  Samples of good AI generated CUDA kernels
  ☆84Updated last month
• salykova / sgemm.cu
  High-Performance SGEMM on CUDA devices
  ☆97Updated 5 months ago
• huggingface / optimum-amd
  AMD related optimizations for transformer models
  ☆80Updated 3 weeks ago
• Infini-AI-Lab / UMbreLLa
  LLM Inference on consumer devices
  ☆121Updated 4 months ago
• sekstini / gpupoor
  ☆17Updated 7 months ago
• abacusai / gh200-llm
  Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuning
  ☆46Updated 4 months ago
• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆153Updated 9 months ago
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆160Updated this week
• gevtushenko / llm.c
  LLM training in simple, raw C/CUDA
  ☆99Updated last year
• intel / neural-speed
  An innovative library for efficient LLM inference via low-bit quantization
  ☆349Updated 10 months ago
• ROCm / aiter
  AI Tensor Engine for ROCm
  ☆232Updated this week
• abetlen / ggml-python
  Python bindings for ggml
  ☆142Updated 10 months ago
• OpenGVLab / EfficientQAT
  [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  ☆277Updated last month
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆135Updated this week
• gpu-mode / ring-attention
  ring-attention experiments
  ☆143Updated 9 months ago
• ROCm / triton
  Development repository for the Triton language and compiler
  ☆125Updated this week
• OpenMachine-ai / transformer-tricks
  A collection of tricks and tools to speed up transformer models
  ☆170Updated last month
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆330Updated last week