Alternatives and similar repositories for torchair

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

• AlibabaPAI / FLASHNN
  ☆102Updated last year
• flashinfer-ai / cutlass-viz
  ☆65Updated 6 months ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆82Updated this week
• InternLM / turbomind
  ☆97Updated 7 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆78Updated this week
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆39Updated last year
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆124Updated 6 months ago
• thunlp / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆32Updated 2 months ago
• madsys-dev / deepseekv2-profile
  ☆151Updated 8 months ago
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆142Updated last month
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆50Updated 2 months ago
• FlagTree / libtriton_jit
  A Triton JIT runtime and ffi provider in C++
  ☆29Updated last week
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 6 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆114Updated 5 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆183Updated last month
• LeiWang1999 / Stream-k.tvm
  ☆19Updated last year
• feifeibear / DPSKV3MFU
  Estimate MFU for DeepSeekV3
  ☆26Updated 10 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆100Updated 4 months ago
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆32Updated 9 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.
  ☆45Updated 5 months ago
• tile-ai / tilescale
  Tile-based language built for AI computation across all scales
  ☆78Updated this week
• tile-ai / TileOPs
  ☆56Updated last week
• microsoft / AttentionEngine
  ☆106Updated 5 months ago
• deepspeedai / DeepSpeed-Kernels
  ☆71Updated 7 months ago
• alibaba / easydist
  Automated Parallelization System and Infrastructure for Multiple Ecosystems
  ☆80Updated 11 months ago
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆42Updated 8 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆51Updated last year
• FlagOpen / FlagCX
  ☆125Updated last week