Alternatives and similar repositories for mirage

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

• HazyResearch / ThunderKittens
  Tile primitives for speedy kernels
  ☆3,075Updated this week
• ByteDance-Seed / Triton-distributed
  Distributed Compiler based on Triton for Parallel Systems
  ☆1,315Updated 3 weeks ago
• tspeterkim / flash-attention-minimal
  Flash Attention in ~100 lines of CUDA (forward pass only)
  ☆1,044Updated last year
• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆4,707Updated this week
• tile-ai / tilelang
  Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
  ☆4,739Updated this week
• Dao-AILab / quack
  A Quirky Assortment of CuTe Kernels
  ☆749Updated this week
• HazyResearch / Megakernels
  kernels, of the mega variety
  ☆648Updated 3 months ago
• srush / Triton-Puzzles
  Puzzles for learning Triton
  ☆2,226Updated last year
• efeslab / Nanoflow
  A throughput-oriented high-performance serving framework for LLMs
  ☆937Updated 2 months ago
• NVIDIA / cutile-python
  cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
  ☆1,824Updated last week
• siboehm / SGEMM_CUDA
  Fast CUDA matrix multiplication from scratch
  ☆1,023Updated 4 months ago
• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆1,224Updated 4 months ago
• ScalingIntelligence / KernelBench
  KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
  ☆763Updated this week
• thuml / depyf
  depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
  ☆778Updated 3 months ago
• flagos-ai / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆871Updated this week
• microsoft / BitBLAS
  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
  ☆743Updated 5 months ago
• mit-han-lab / omniserve
  [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…
  ☆802Updated 10 months ago
• NVIDIA / TransformerEngine
  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…
  ☆3,092Updated this week
• perplexityai / pplx-kernels
  Perplexity GPU Kernels
  ☆553Updated 2 months ago
• SiriusNEO / Triton-Puzzles-Lite
  Puzzles for learning Triton, play it with minimal environment configuration!
  ☆595Updated 3 weeks ago
• pytorch / helion
  A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
  ☆711Updated last week
• volcengine / veScale
  Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
  ☆917Updated last month
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆987Updated last year
• pranjalssh / fast.cu
  Fastest kernels written from scratch
  ☆523Updated 4 months ago
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆717Updated 2 weeks ago
• sgl-project / mini-sglang
  A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
  ☆2,924Updated 2 weeks ago
• NVIDIA / Model-Optimizer
  A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…
  ☆1,848Updated this week
• NVIDIA / TileGym
  Helpful kernel tutorials and examples for tile-based GPU programming
  ☆568Updated last week
• andrewkchan / yalm
  Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
  ☆547Updated 4 months ago
• pytorch / ao
  PyTorch native quantization and sparsity for training and inference
  ☆2,631Updated this week