feifeibear / ChituAttention

Related projects ⓘ

Alternatives and complementary repositories for ChituAttention

• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆36Updated 6 months ago
• LeiWang1999 / Stream-k.tvm
  ☆18Updated last month
• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆55Updated last month
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆57Updated 5 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆53Updated 3 weeks ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆52Updated 3 months ago
• AlibabaPAI / FLASHNN
  ☆79Updated 2 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.
  ☆23Updated 2 weeks ago
• ruikangliu / FlatQuant
  Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization
  ☆63Updated last week
• CalebDu / Awesome-Cute
  ☆16Updated this week
• shadowpa0327 / Palu
  Code for Palu: Compressing KV-Cache with Low-Rank Projection
  ☆57Updated this week
• InternLM / turbomind
  ☆35Updated 2 weeks ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆32Updated 3 months ago
• flashinfer-ai / debug-print
  Debug print operator for cudagraph debugging
  ☆10Updated 3 months ago
• madsys-dev / deepseekv2-profile
  ☆64Updated 3 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆26Updated 5 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆98Updated 2 months ago
• mlc-ai / xgrammar
  Efficient, Flexible and Portable Structured Generation
  ☆40Updated this week
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆85Updated 8 months ago
• d-matrix-ai / keyformer-llm
  ☆42Updated 7 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆59Updated last week
• TileLang / tvm
  Open deep learning compiler stack for cpu, gpu and specialized accelerators
  ☆15Updated this week
• microsoft / chunk-attention
  ☆42Updated 6 months ago
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated 11 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆154Updated this week
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆51Updated 2 months ago
• hao-ai-lab / MuxServe
  ☆46Updated 5 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆90Updated 4 months ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆48Updated 4 months ago