Alternatives and similar repositories for llm-deploy

Users that are interested in llm-deploy are comparing it to the libraries listed below

• CalvinXKY / BasicCUDA
  A tutorial for CUDA&PyTorch
  ☆173Updated 11 months ago
• OpenPPL / ppl.llm.serving
  ☆130Updated last year
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆167Updated 3 months ago
• OpenPPL / ppl.nn.llm
  ☆141Updated last year
• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated 11 months ago
• OpenPPL / ppl.pmx
  ☆60Updated last year
• flagos-ai / FlagCX
  ☆137Updated this week
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆242Updated last month
• AyakaGEMM / Hands-on-GEMM
  ☆144Updated last year
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆132Updated 2 years ago
• 66RING / tiny-flash-attention
  flash attention tutorial written in python, triton, cuda, cutlass
  ☆468Updated 7 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆63Updated last year
• 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.
  ☆44Updated 10 months ago
• ifromeast / cuda_learning
  learning how CUDA works
  ☆359Updated 9 months ago
• YuxueYang1204 / CudaDemo
  Implement custom operators in PyTorch with cuda/c++
  ☆74Updated 2 years ago
• BBuf / how-to-learn-deep-learning-framework
  how to learn PyTorch and OneFlow
  ☆466Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆140Updated 7 months ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆263Updated 5 months ago
• CalebDu / Awesome-Cute
  ☆112Updated 7 months ago
• madsys-dev / deepseekv2-profile
  ☆153Updated 9 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆113Updated 5 months ago
• iclementine / optimize_softmax
  Optimize softmax in triton in many cases
  ☆21Updated last year
• AlibabaPAI / FLASHNN
  ☆104Updated last year
• LDLINGLINGLING / nano_vllm_note
  注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
  ☆126Updated 4 months ago
• Tencent / KsanaLLM
  ☆518Updated last month
• InfiniTensor / RefactorGraph
  分层解耦的深度学习推理引擎
  ☆78Updated 10 months ago
• zeroine / cutlass-cute-sample
  ☆48Updated last year
• flagos-ai / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆811Updated this week
• flagos-ai / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆430Updated last week