Alternatives and similar repositories for whl

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

• flashinfer-ai / cutlass-viz
  ☆65Updated 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.
  ☆46Updated 8 months ago
• tile-ai / AttentionEngine
  ☆52Updated 8 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 9 months ago
• microsoft / AttentionEngine
  ☆118Updated 8 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated last year
• KuangjuX / AttnLink
  An experimental communicating attention kernel based on DeepEP.
  ☆35Updated 6 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆56Updated last year
• InternLM / turbomind
  ☆96Updated 10 months ago
• zhuzilin / flash-attention-with-sink
  ☆38Updated 6 months ago
• Bruce-Lee-LY / cutlass_gemm
  Multiple GEMM operators are constructed with cutlass to support LLM inference.
  ☆20Updated 6 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆142Updated last year
• ByteDance-Seed / cudaLLM
  ☆130Updated 5 months ago
• BBuf / tensorrt-llm-moe
  ☆34Updated last year
• flashinfer-ai / debug-print
  Debug print operator for cudagraph debugging
  ☆14Updated last year
• ACA-Lab-SJTU / token-ring
  ☆13Updated last year
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆96Updated 4 months ago
• HydraQYH / hp_rms_norm
  High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)
  ☆26Updated 3 weeks ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆85Updated last year
• feifeibear / DPSKV3MFU
  Estimate MFU for DeepSeekV3
  ☆26Updated last year
• cherichy / tilecute
  ☆32Updated 7 months ago
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆51Updated 7 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆79Updated last year
• sgl-project / sgl-flash-attn
  Fast and memory-efficient exact attention
  ☆18Updated 2 weeks ago
• microsoft / chunk-attention
  ☆85Updated 9 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆92Updated 2 weeks ago
• AlibabaPAI / FLASHNN
  ☆105Updated last year
• microsoft / tokenweave
  Accepted to MLSys 2026
  ☆70Updated 2 weeks ago
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆36Updated last year
• flagos-ai / libtriton_jit
  A Triton JIT runtime and ffi provider in C++
  ☆31Updated 2 weeks ago