Alternatives and similar repositories for DeepSpeed-Kernels

Users that are interested in DeepSpeed-Kernels are comparing it to the libraries listed below

• hpcaitech / TensorNVMe
  A Python library transfers PyTorch tensors between CPU and NVMe
  ☆121Updated 11 months ago
• stanford-futuredata / stk
  ☆112Updated last year
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆127Updated 5 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆85Updated last year
• triton-lang / kernels
  ☆93Updated last year
• InternLM / turbomind
  ☆97Updated 7 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆85Updated last month
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆271Updated 3 months ago
• microsoft / AttentionEngine
  ☆106Updated 5 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆90Updated 7 months ago
• anyscale / llm-continuous-batching-benchmarks
  ☆121Updated last year
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆78Updated last year
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆120Updated last year
• flashinfer-ai / cutlass-viz
  ☆65Updated 6 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
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆130Updated 11 months ago
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆102Updated 7 years ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆51Updated last year
• INT-FlashAttention2024 / INT-FlashAttention
  ☆83Updated 9 months ago
• AlibabaPAI / FLASHNN
  ☆101Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆169Updated last year
• meta-pytorch / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆303Updated 2 months ago
• open-lm-engine / accelerated-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆64Updated this week
• neuralmagic / AutoFP8
  ☆205Updated 6 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆97Updated last week
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆216Updated last week
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆217Updated last year
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆39Updated last year
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 6 months ago