Alternatives and similar repositories for DeepSpeed-Kernels

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

• stanford-futuredata / stk
  ☆110Updated 11 months ago
• hpcaitech / TensorNVMe
  A Python library transfers PyTorch tensors between CPU and NVMe
  ☆120Updated 8 months ago
• InternLM / turbomind
  ☆92Updated 4 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆80Updated 11 months ago
• triton-lang / kernels
  ☆86Updated 9 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆80Updated last week
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆261Updated last month
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆109Updated 2 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆88Updated 4 months ago
• anyscale / llm-continuous-batching-benchmarks
  ☆120Updated last year
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆76Updated last year
• microsoft / AttentionEngine
  ☆77Updated 3 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆113Updated last year
• neuralmagic / AutoFP8
  ☆195Updated 3 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆111Updated 11 months ago
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆149Updated last week
• flashinfer-ai / cutlass-viz
  ☆61Updated 3 months ago
• meta-pytorch / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆204Updated last week
• meta-pytorch / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆290Updated 2 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• jundaf2 / INT8-Flash-Attention-FMHA-Quantization
  ☆159Updated last year
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆208Updated last week
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆94Updated last month
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆119Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆124Updated 8 months ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆149Updated 10 months ago
• AlibabaPAI / FLASHNN
  ☆97Updated 11 months ago
• open-lm-engine / flash-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆58Updated this week
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆54Updated 7 months ago
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆214Updated last year