Alternatives and similar repositories for FasterLLaMA

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

• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆143Updated this week
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆74Updated 11 months ago
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆22Updated 6 months ago
• AyakaGEMM / Hands-on-GEMM
  ☆137Updated last year
• caijixueIT / CUDA_Learning_for_Freshman
  ☆11Updated 4 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.
  ☆40Updated last month
• OpenPPL / ppl.llm.kernel.cuda
  ☆149Updated 6 months ago
• CalebDu / Awesome-Cute
  ☆89Updated 2 months ago
• BBuf / tensorrt-llm-moe
  ☆31Updated 6 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆91Updated 2 months ago
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆44Updated 11 months ago
• Bruce-Lee-LY / cutlass_gemm
  Multiple GEMM operators are constructed with cutlass to support LLM inference.
  ☆18Updated 2 weeks ago
• 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.
  ☆39Updated 5 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆99Updated 3 weeks ago
• xlite-dev / ffpa-attn
  ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.🎉
  ☆194Updated 2 months ago
• zeroine / cutlass-cute-sample
  ☆37Updated last year
• InfiniTensor / RefactorGraph
  分层解耦的深度学习推理引擎
  ☆74Updated 5 months ago
• OpenPPL / ppl.pmx
  ☆59Updated 8 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆63Updated 10 months ago
• CalvinXKY / BasicCUDA
  A tutorial for CUDA&PyTorch
  ☆150Updated 6 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆92Updated 7 months ago
• pzhao-eng / FlashMLA
  ☆51Updated 2 weeks ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆93Updated 2 weeks ago
• weishengying / cute_gemm
  ☆14Updated 11 months ago
• FlagOpen / FlagCX
  ☆80Updated last week
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆111Updated 10 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• zjhellofss / triton_course
  ☆31Updated 2 months ago
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆76Updated 3 months ago
• FlagTree / flagtree
  FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.
  ☆65Updated this week