Alternatives and similar repositories for Efficient-LLM-Inferencing-on-GPUs

Users that are interested in Efficient-LLM-Inferencing-on-GPUs are comparing it to the libraries listed below

• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆55Updated 11 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆96Updated 3 months ago
• AlibabaPAI / FLASHNN
  ☆102Updated last year
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆230Updated 2 years ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆70Updated last year
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆92Updated 2 years ago
• gty111 / GEMM_MMA
  Optimize GEMM with tensorcore step by step
  ☆36Updated 2 years 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.
  ☆43Updated 9 months ago
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆59Updated 8 months ago
• microsoft / SparTA
  ☆163Updated last year
• 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 6 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆137Updated 7 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆119Updated 7 months ago
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆190Updated 10 months ago
• UDC-GAC / venom
  A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores
  ☆56Updated 2 years ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated 11 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆123Updated last year
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆84Updated this week
• toyaix / TritonLLM
  LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model
  ☆61Updated 2 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆78Updated last year
• mit-han-lab / parallel-computing-tutorial
  ☆176Updated 2 years ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆97Updated last year
• JackonYang / hands-on-tvm
  hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.
  ☆49Updated 2 years ago
• tile-ai / tilescale
  Tile-based language built for AI computation across all scales
  ☆98Updated this week
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆94Updated 6 months ago
• zeroine / cutlass-cute-sample
  ☆48Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆113Updated 5 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• OpenBitSys / BitDecoding
  [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆69Updated last week
• microsoft / chunk-attention
  ☆83Updated 8 months ago