Alternatives and similar repositories for onnxruntime-server

Users that are interested in onnxruntime-server are comparing it to the libraries listed below

• rtzr / tritony
  Tiny configuration for Triton Inference Server
  ☆45Updated last year
• kibae / pg_onnx
  pg_onnx: ONNX Runtime integrated with PostgreSQL. Perform ML inference with data in your database.
  ☆57Updated 2 months ago
• RahulSChand / llama2.c-for-dummies
  Step by step explanation/tutorial of llama2.c
  ☆225Updated 2 years ago
• sionic-ai / BGE-M3-Model-Converter
  A tool for manual conversion of BGE-M3 models with preserved trainable variables and direct control over model outputs.
  ☆44Updated 4 months ago
• dnotitia / smoothie-qwen
  A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
  ☆103Updated 6 months ago
• jwj7140 / Gugugo
  Gugugo: 한국어 오픈소스 번역 모델 프로젝트
  ☆83Updated last year
• lablup / all-smi
  Command-line utility for monitoring GPU hardware.
  ☆106Updated last week
• Curt-Park / mnist-fastapi-celery-triton
  Simple example of FastAPI + Celery + Triton for benchmarking
  ☆64Updated 3 years ago
• sionic-ai / Llama4-Token-Editor
  ☆64Updated 5 months ago
• mirusu400 / CLOVA-X
  Unofficial API for CLOVA X
  ☆37Updated 2 years ago
• qwopqwop200 / ko-arena-hard-auto
  Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean
  ☆22Updated 8 months ago
• Curt-Park / mnist-fastapi-aio-triton
  Simple example of FastAPI + gRPC AsyncIO + Triton
  ☆69Updated 3 years ago
• Marker-Inc-Korea / Korean-SAT-LLM-Leaderboard
  Korean SAT leader board
  ☆169Updated last month
• Marker-Inc-Korea / RAGchain
  Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...
  ☆284Updated 2 years ago
• SqueezeBits / Torch-TRTLLM
  Ditto is an open-source framework that enables direct conversion of HuggingFace PreTrainedModels into TensorRT-LLM engines.
  ☆53Updated 5 months ago
• 42dot / 42dot_LLM
  42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to …
  ☆130Updated last year
• newfull5 / NLLB-200-Distilled-350M-en-ko
  nllb-200 distilled 350M for English to Korean translation
  ☆28Updated last year
• trailerAI / KoTAN
  KoTAN: Korean Translation and Augmentation with fine-tuned NLLB
  ☆23Updated 2 years ago
• sionic-ai / llama-3.1-xionic-ko-70b
  ☆25Updated last year
• sionic-ai / xionic
  ☆48Updated last year
• wangkuiyi / huggingface-tokenizer-in-cxx
  ☆70Updated 2 years ago
• jinhoyoo / summarize_youtube_video_lecture
  Summarize Youtube's script by chapter creater configured
  ☆26Updated last year
• gyunggyung / KoAlpaca.cpp
  Locally run an Instruction-Tuned Chat-Style LLM KoAlpaca
  ☆24Updated 2 years ago
• NAVER-Cloud-HyperCLOVA-X / OmniServe
  ☆51Updated last week
• instructkr / LogicKor
  한국어 언어모델 다분야 사고력 벤치마크
  ☆200Updated last year
• StableFluffy / EasyLLMFeaturePorter
  1-Click is all you need.
  ☆63Updated last year
• LG-AI-EXAONE / EXAONE-3.5
  Official repository for EXAONE 3.5 built by LG AI Research
  ☆203Updated last year
• smarteasy / open-prompt
  ☆19Updated 2 weeks ago
• sionic-ai / webgpu-llm-loader
  A loader that lets you try running LLMs built for WebGPU.
  ☆29Updated 2 years ago
• sionic-ai / serverless-rag-mcp-server
  ☆39Updated 10 months ago