vllm-project / flash-attention

Related projects ⓘ

Alternatives and complementary repositories for flash-attention

• AlibabaPAI / FLASHNN
  ☆79Updated 2 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆87Updated 3 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆98Updated last month
• INT-FlashAttention2024 / INT-FlashAttention
  ☆45Updated last month
• microsoft / DeepSpeed-Kernels
  ☆55Updated 5 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆85Updated 8 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆74Updated 7 months ago
• madsys-dev / deepseekv2-profile
  ☆63Updated 3 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆35Updated 6 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆51Updated last week
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆196Updated last week
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆47Updated 4 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆177Updated last year
• ColfaxResearch / cutlass-kernels
  ☆162Updated 3 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆24Updated this week
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆75Updated this week
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆51Updated 2 months ago
• hpcaitech / TensorNVMe
  A Python library transfers PyTorch tensors between CPU and NVMe
  ☆96Updated this week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆53Updated 4 months ago
• OpenPPL / ppl.nn.llm
  ☆140Updated 6 months ago
• mit-han-lab / deepcompressor
  ☆121Updated this week
• 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.
  ☆26Updated 2 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆48Updated 2 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆67Updated 3 months ago
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆79Updated 5 months ago
• ColfaxResearch / cfx-article-src
  ☆47Updated 2 weeks ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆215Updated 5 months ago
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆59Updated 6 years ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆222Updated this week
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆75Updated 3 weeks ago