#Vllm

Showing 60 of 95 repositories tagged #vllm, ranked by stars

modelscope
modelscope
FunASR

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

Score
100
β˜… 19.0k β‘‚ 1.9k +29/day
Python
meta-llama
meta-llama
llama-cookbook

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

Score
91
β˜… 18.4k β‘‚ 2.7k +7/day
Jupyter Notebook
LMCache
LMCache
LMCache

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Score
82
β˜… 10.4k β‘‚ 1.5k +115/day
Python
OpenRLHF
OpenRLHF
OpenRLHF

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Score
73
β˜… 9.8k β‘‚ 982 +65/day
Python
xorbitsai
xorbitsai
inference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop β€” all through one unified, production-ready inference API.

Score
64
β˜… 9.4k β‘‚ 845 β€”
Python
ai-dynamo
ai-dynamo
dynamo

A Datacenter Scale Distributed Inference Serving Framework

Score
100
β˜… 7.5k β‘‚ 1.3k +2/day
Rust
kvcache-ai
kvcache-ai
Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Score
100
β˜… 5.8k β‘‚ 950 +21/day
C++
kserve
kserve
kserve

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Score
100
β˜… 5.7k β‘‚ 1.6k +2/day
Go
OpenBMB
OpenBMB
UltraRAG

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

Score
55
β˜… 5.6k β‘‚ 434 +4/day
Python
xlite-dev
xlite-dev
Awesome-LLM-Inference

πŸ“šA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.πŸŽ‰

Score
45
β˜… 5.4k β‘‚ 420 +19/day
Python
gpustack
gpustack
gpustack

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

Score
98
β˜… 5.3k β‘‚ 567 β€”
Python
katanaml
katanaml
sparrow

Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM

Score
96
β˜… 5.2k β‘‚ 518 +3/day
Python
mostlygeek
mostlygeek
llama-swap

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Score
50
β˜… 4.9k β‘‚ 370 +45/day
Go
vllm-project
vllm-project
semantic-router

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

Score
75
β˜… 4.9k β‘‚ 742 +16/day
Go
skyzh
skyzh
tiny-llm

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Score
36
β˜… 4.3k β‘‚ 341 +14/day
Python
PaddlePaddle
PaddlePaddle
FastDeploy

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

Score
92
β˜… 3.7k β‘‚ 755 +1/day
Python
lemony-ai
lemony-ai
cascadeflow

Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.

Score
27
β˜… 3.2k β‘‚ 670 +73/day
Python
containers
containers
ramalama

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

Score
91
β˜… 3.0k β‘‚ 347 +9/day
Python
vllm-project
vllm-project
vllm-ascend

Community maintained hardware plugin for vLLM on Ascend

Score
94
β˜… 2.5k β‘‚ 1.7k +90/day
C++
intel
intel
auto-round

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

Score
18
β˜… 1.5k β‘‚ 150 +6/day
Python
waybarrios
waybarrios
vllm-mlx

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

Score
89
β˜… 1.4k β‘‚ 195 +14/day
Python
SemiAnalysisAI
SemiAnalysisAI
InferenceX

Open Source Continuous Inference Benchmark Research Platform β€” Kimi K2.7-Code, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soonβ„’ TPUv6e/v7/Trainium2/3 | εΌ€ζΊζŒη»­ζŽ¨η†εŸΊε‡†η ”η©ΆεΉ³ε° β€” Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72οΌŒε³ε°†ζŽ¨ε‡Ίβ„’ TPUv6e/v7/Trainium2/3

Score
87
β˜… 1.2k β‘‚ 223 +2/day
Python
kubeai-project
kubeai-project
kubeai

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

Score
100
β˜… 1.2k β‘‚ 128 +6/day
Go
bricks-cloud
bricks-cloud
BricksLLM

πŸ”’ Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports OpenAI, Azure OpenAI, Anthropic, vLLM, and open-source LLMs.

Score
50
β˜… 1.2k β‘‚ 94 +2/day
Go
prometheus-eval
prometheus-eval
prometheus-eval

Evaluate your LLM's response with Prometheus and GPT4 πŸ’―

Score
45
β˜… 1.1k β‘‚ 71 +5/day
Python
ovg-project
ovg-project
kvcached

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

Score
85
β˜… 1.1k β‘‚ 122 +1/day
Python
jmaczan
jmaczan
tiny-vllm

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

Score
75
β˜… 882 β‘‚ 61 +51/day
C++
harleyszhang
harleyszhang
llm_note

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Score
77
β˜… 882 β‘‚ 88 β€”
Python
jakobdylanc
jakobdylanc
llmcord

Make Discord your LLM frontend - Supports any OpenAI compatible API (OpenRouter, Ollama and more)

Score
83
β˜… 813 β‘‚ 198 β€”
Python
varunvasudeva1
varunvasudeva1
llm-server-docs

End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.

Score
91
β˜… 804 β‘‚ 59 β€”
pgalko
pgalko
BambooAI

A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.

Score
9
β˜… 783 β‘‚ 83 +1/day
Python
th1nhhdk
th1nhhdk
local_ai_ocr

An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR-2 AI (running directly on your machine).

Score
79
β˜… 763 β‘‚ 189 β€”
Python
ModelTC
ModelTC
LightCompress

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

Score
74
β˜… 731 β‘‚ 78 β€”
Python
microsoft
microsoft
vidur

Accurate, large-scale, and extensible simulator for LLM inference Systems

Score
40
β˜… 639 β‘‚ 120 +2/day
Python
SimonZeng7108
SimonZeng7108
efficientsam3

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

Score
100
β˜… 625 β‘‚ 48 +6/day
Jupyter Notebook
raids-lab
raids-lab
crater

Crater is a cloud-native AI training & inference platform.

Score
82
β˜… 540 β‘‚ 67 +1/day
TypeScript
openinfer-project
openinfer-project
openinfer

Pure Rust + CUDA LLM inference engine β€” no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Score
0
β˜… 526 β‘‚ 75 +5/day
Rust
Chen-zexi
Chen-zexi
vllm-cli

A command-line interface tool for serving LLM using vLLM.

Score
55
β˜… 505 β‘‚ 28 β€”
Python
ome-projects
ome-projects
ome

Open Model Engine (OME) β€” Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

Score
72
β˜… 477 β‘‚ 83 +1/day
Go
runpod-workers
runpod-workers
worker-vllm

The Runpod worker template for serving our large language model endpoints. Powered by vLLM.

Score
81
β˜… 455 β‘‚ 376 β€”
Python
neosun100
neosun100
DeepSeek-OCR-WebUI

🎨 Ready-to-use DeepSeek-OCR Web UI | Modern Interface | 7 Recognition Modes | Batch Processing | Real-time Logging | Fully Responsive

Score
50
β˜… 435 β‘‚ 94 +1/day
TypeScript
huawei-csl
huawei-csl
KVarN

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

Score
62
β˜… 434 β‘‚ 28 +4/day
Python
jaylfc
jaylfc
taOS

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

Score
68
β˜… 411 β‘‚ 31 β€”
Python
chtmp223
chtmp223
topicGPT

TopicGPT: A Prompt-Based Framework for Topic Modeling [NAACL'24]

Score
66
β˜… 410 β‘‚ 66 β€”
Python
AEON-7
AEON-7
Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

Score
64
β˜… 403 β‘‚ 41 +3/day
Python
FujitsuResearch
FujitsuResearch
OneCompression

Python package for LLM compression

Score
60
β˜… 396 β‘‚ 18 +2/day
Python
varunshenoy
varunshenoy
super-json-mode

Low latency JSON generation using LLMs ⚑️

Score
25
β˜… 396 β‘‚ 14 β€”
Jupyter Notebook
lightseekorg
lightseekorg
smg

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.

Score
70
β˜… 380 β‘‚ 111 +4/day
Rust
guqiong96
guqiong96
Lvllm

LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.

Score
0
β˜… 380 β‘‚ 34 +3/day
Python
jasonacox
jasonacox
TinyLLM

Setup and run a local LLM and Chatbot using consumer grade hardware.

Score
51
β˜… 342 β‘‚ 38 +1/day
JavaScript
InftyAI
InftyAI
llmaz

☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!

Score
73
β˜… 307 β‘‚ 46 +1/day
Go
pensarai
pensarai
apex

AI-powered offensive security testing using autonomous agents, directly in your terminal.

Score
100
β˜… 293 β‘‚ 55 β€”
TypeScript
vortico
vortico
flama

The production framework for Predictive and Generative AI. Serve any model as an API in one line, with OpenAI/Anthropic/Ollama-compatible endpoints, a built-in chat UI, and native MCP.

Score
57
β˜… 291 β‘‚ 17 β€”
Python
guoqingbao
guoqingbao
xinfer

Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.

Score
58
β˜… 283 β‘‚ 40 +8/day
Rust
matrixhub-ai
matrixhub-ai
matrixhub

An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.

Score
0
β˜… 255 β‘‚ 31 +2/day
Go
thushan
thushan
olla

High-performance lightweight proxy and load balancer for LLM infrastructure. Intelligent routing, automatic failover and unified model discovery across local and remote inference backends.

Score
25
β˜… 254 β‘‚ 36 β€”
Go
yoziru
yoziru
nextjs-vllm-ui

Fully-featured, beautiful web interface for vLLM - built with NextJS.

Score
0
β˜… 187 β‘‚ 31 +1/day
TypeScript
gotzmann
gotzmann
booster

Booster - open accelerator for LLM models. Better inference and debugging for AI hackers

Score
17
β˜… 168 β‘‚ 13 β€”
C++
defilantech
defilantech
LLMKube

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU, autoscaling, air-gapped, production-ready.

Score
64
β˜… 163 β‘‚ 24 +1/day
Go
OpenDCAI
OpenDCAI
One-Eval

Automated system for LLM evaluation via agents. Doc as below:

Score
0
β˜… 150 β‘‚ 25 +2/day
Python
Related Topics
#llm#inference#llm-inference#ai#sglang#openai#ollama#pytorch#python#qwen#kubernetes#llama

Β© 2026 GitRepoTrend Β· GitHub repositories by topic Β· Updated weekly