Alternatives and similar repositories for serving

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

• Oneflow-Inc / oneflow-lite
  ☆18Updated last year
• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆43Updated 2 years ago
• Oneflow-Inc / oneflow-xrt
  ☆23Updated 2 years ago
• Bruce-Lee-LY / cutlass_gemm
  Multiple GEMM operators are constructed with cutlass to support LLM inference.
  ☆18Updated 9 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆92Updated last week
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆86Updated 2 months ago
• yester31 / Cutlass_EX
  study of cutlass
  ☆21Updated 8 months ago
• BBuf / tensorrt-llm-moe
  ☆31Updated 5 months 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 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.
  ☆38Updated last month
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆110Updated 10 months ago
• vipshop / cache-dit
  🤗CacheDiT: A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers🔥
  ☆99Updated this week
• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• DeepLink-org / CVFusion
  CVFusion is an open-source deep learning compiler to fuse the OpenCV operators.
  ☆30Updated 2 years ago
• AlibabaPAI / FLASHNN
  ☆96Updated 10 months ago
• Oneflow-Inc / conda-env
  ☆12Updated 2 years ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆72Updated 11 months ago
• pigirons / conv3x3_m1
  This is a demo how to write a high performance convolution run on apple silicon
  ☆54Updated 3 years ago
• Ascend / torchair
  ☆16Updated this week
• InternLM / turbomind
  ☆87Updated 3 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• OpenPPL / ppl.llm.serving
  ☆128Updated 6 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆129Updated last year
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• SkyworkAI / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆16Updated last year
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆43Updated 11 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆107Updated last year
• Oneflow-Inc / one-fx
  A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.
  ☆13Updated 2 years ago
• Ascend / AscendSpeed
  ☆79Updated last year