Alternatives and similar repositories for torchair:

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

• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing. By pro…
  ☆70Updated this week
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆39Updated 11 months ago
• LeiWang1999 / Stream-k.tvm
  ☆19Updated 5 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆90Updated last month
• xlite-dev / hgemm-mma
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆62Updated 3 weeks ago
• alibaba / easydist
  Automated Parallelization System and Infrastructure for Multiple Ecosystems
  ☆78Updated 4 months ago
• microsoft / FractalTensor
  ☆24Updated 3 months ago
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆76Updated this week
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆61Updated last week
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆89Updated last year
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆15Updated last month
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆106Updated 6 months ago
• sgl-project / tensorrt-demo
  TensorRT LLM Benchmark Configuration
  ☆13Updated 8 months ago
• heheda12345 / MagPy
  ☆39Updated 9 months ago
• sjtu-epcc / Tacker
  Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
  ☆20Updated last month
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆46Updated last month
• chips-compilers-mlsys-21 / chips-compilers-mlsys-21.github.io
  ☆11Updated 3 years ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆93Updated last year
• AlibabaPAI / FLASHNN
  ☆88Updated 6 months ago
• TiledTensor / TiledLower
  ThrillerFlow is a Dataflow Analysis and Codegen Framework written in Rust.
  ☆14Updated 4 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆35Updated 2 weeks ago
• FlagOpen / FlagCX
  ☆45Updated this week
• cassiewilliam / cuda_op_benchmark
  方便扩展的Cuda算子理解和优化框架，仅用在学习使用
  ☆13Updated 9 months ago
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆27Updated 3 weeks ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆29Updated this week
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated last year
• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆21Updated 2 months ago
• apuaaChen / EVT_AE
  Artifacts of EVT ASPLOS'24
  ☆24Updated last year
• ROCm / TransformerEngine
  ☆25Updated this week
• mlc-ai / mlc-python
  ☆26Updated last week