Alternatives and similar repositories for open-gpu-kernel-modules

Users that are interested in open-gpu-kernel-modules are comparing it to the libraries listed below

• LeanModels / DFloat11
  DFloat11: Lossless LLM Compression for Efficient GPU Inference
  ☆562Updated this week
• CerebrasResearch / reap
  REAP: Router-weighted Expert Activation Pruning for SMoE compression
  ☆119Updated 3 weeks ago
• Cornell-RelaxML / qtip
  ☆156Updated 5 months ago
• ReinForce-II / mmapeak
  ☆46Updated last month
• ScalingIntelligence / good-kernels
  Samples of good AI generated CUDA kernels
  ☆92Updated 6 months ago
• Infini-AI-Lab / UMbreLLa
  LLM Inference on consumer devices
  ☆125Updated 8 months ago
• NimbleEdge / sparse_transformers
  Sparse Inferencing for transformer based LLMs
  ☆213Updated 3 months ago
• SJTU-IPADS / Bamboo
  Bamboo-7B Large Language Model
  ☆92Updated last year
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆61Updated last year
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆201Updated last month
• vllm-project / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆210Updated last week
• inferx-net / inferx
  InferX: Inference as a Service Platform
  ☆139Updated this week
• Cornell-RelaxML / yaqa-quantization
  ☆63Updated 5 months ago
• jukofyork / transplant-vocab
  Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.
  ☆46Updated last month
• tdrussell / qlora-pipe
  A pipeline parallel training script for LLMs.
  ☆163Updated 7 months ago
• leafspark / AutoGGUF
  automatically quant GGUF models
  ☆217Updated last month
• 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…
  ☆48Updated last year
• BlinkDL / fast.c
  Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.
  ☆73Updated 9 months ago
• turboderp-org / exllamav3
  An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
  ☆586Updated this week
• mag- / gpu_benchmark
  Gpu benchmark
  ☆73Updated 10 months ago
• matt-c1 / llama-3-quant-comparison
  Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.
  ☆165Updated last year
• WaveSpeedAI / QuantumAttention
  [WIP] Better (FP8) attention for Hopper
  ☆32Updated 9 months ago
• wdlctc / headinfer
  ☆60Updated 6 months ago
• powerserve-project / PowerServe
  High-speed and easy-use LLM serving framework for local deployment
  ☆137Updated 3 months ago
• chu-tianxiang / llama-cpp-torch
  llama.cpp to PyTorch Converter
  ☆34Updated last year
• bjj / exllamav2-openai-server
  An OpenAI API compatible LLM inference server based on ExLlamaV2.
  ☆25Updated last year
• KONAKONA666 / q8_kernels
  ☆77Updated 11 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆143Updated 9 months ago
• Thireus / GGUF-Tool-Suite
  Input your VRAM and RAM and the toolchain will produce a GGUF model tuned to your system within seconds — flexible model sizing and lowes…
  ☆65Updated last week
• chigkim / Ollama-MMLU-Pro
  ☆107Updated 3 months ago