Alternatives and similar repositories for serving

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

• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆43Updated 2 years ago
• Oneflow-Inc / oneflow-lite
  ☆18Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆93Updated 2 months ago
• BBuf / tensorrt-llm-moe
  ☆31Updated 6 months ago
• vipshop / cache-dit
  🤗A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers.
  ☆117Updated this week
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆61Updated last week
• Bruce-Lee-LY / cutlass_gemm
  Multiple GEMM operators are constructed with cutlass to support LLM inference.
  ☆18Updated this week
• 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
• 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
• Oneflow-Inc / conda-env
  ☆12Updated 2 years ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆111Updated 10 months ago
• yester31 / Cutlass_EX
  study of cutlass
  ☆22Updated 8 months ago
• Oneflow-Inc / oneflow-xrt
  ☆23Updated 2 years ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆94Updated 3 weeks ago
• InternLM / turbomind
  ☆92Updated 4 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated 2 years ago
• latentCall145 / channels-last-groupnorm
  A CUDA kernel for NHWC GroupNorm for PyTorch
  ☆19Updated 8 months ago
• AlibabaPAI / FLASHNN
  ☆96Updated 10 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆72Updated last year
• pigirons / conv3x3_m1
  This is a demo how to write a high performance convolution run on apple silicon
  ☆54Updated 3 years ago
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆57Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆110Updated last year
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆129Updated last year
• OpenPPL / ppl.llm.serving
  ☆128Updated 7 months ago
• flashinfer-ai / cutlass-viz
  ☆60Updated 3 months ago
• 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
• 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
• deepspeedai / DeepSpeed-Kernels
  ☆74Updated 4 months ago
• DeepLink-org / CVFusion
  CVFusion is an open-source deep learning compiler to fuse the OpenCV operators.
  ☆31Updated 2 years ago