Alternatives and similar repositories for vllm-openvino

Users that are interested in vllm-openvino are comparing it to the libraries listed below

• openvinotoolkit / openvino.genai
  Run Generative AI models with simple C++/Python API and using OpenVINO Runtime
  ☆371Updated this week
• ROCm / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆108Updated this week
• intel / xFasterTransformer
  ☆431Updated 2 months ago
• intel / intel-xpu-backend-for-triton
  OpenAI Triton backend for Intel® GPUs
  ☆219Updated this week
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆204Updated last month
• openvinotoolkit / openvino_tokenizers
  OpenVINO Tokenizers extension
  ☆42Updated this week
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆97Updated 2 weeks ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆89Updated 5 months ago
• intel / intel-extension-for-deepspeed
  Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note…
  ☆63Updated 4 months ago
• triton-lang / triton-cpu
  An experimental CPU backend for Triton
  ☆160Updated last week
• huggingface / optimum-amd
  AMD related optimizations for transformer models
  ☆95Updated last month
• huggingface / optimum-intel
  🤗 Optimum Intel: Accelerate inference with Intel optimization tools
  ☆507Updated this week
• flagos-ai / FlagCX
  ☆126Updated this week
• openvinotoolkit / npu_compiler
  OpenVINO Intel NPU Compiler
  ☆73Updated last week
• powerserve-project / PowerServe
  High-speed and easy-use LLM serving framework for local deployment
  ☆134Updated 3 months ago
• mlc-ai / relax
  ☆169Updated last week
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆200Updated last month
• flagos-ai / flagtree
  FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.
  ☆131Updated last week
• ROCm / TransformerEngine
  ☆51Updated this week
• intel / neural-speed
  An innovative library for efficient LLM inference via low-bit quantization
  ☆349Updated last year
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆168Updated 7 months ago
• argonne-lcf / LLM-Inference-Bench
  LLM-Inference-Bench
  ☆57Updated 4 months ago
• vllm-project / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆204Updated last week
• HabanaAI / vllm-fork
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆85Updated last week
• intel / llm-on-ray
  Pretrain, finetune and serve LLMs on Intel platforms with Ray
  ☆131Updated last month
• bytedance / ByteMLPerf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆268Updated 3 months ago
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆30Updated last year
• InternLM / turbomind
  ☆97Updated 7 months ago
• intel / torch-xpu-ops
  ☆61Updated this week
• intel / auto-round
  Advanced quantization toolkit for LLMs. Native support for WOQ, MXFP4, NVFP4, GGUF, Adaptive Bits and seamless integration with Transform…
  ☆712Updated this week