#Llm-inference

Showing 60 of 174 repositories tagged #llm-inference, ranked by stars

ray-project
ray-project
ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Score
100
โ˜… 43.2k โ‘‚ 7.8k +6/day
Python
gitleaks
gitleaks
gitleaks

Find secrets with Gitleaks ๐Ÿ”‘

Score
100
โ˜… 28.0k โ‘‚ 2.1k +49/day
Go
liguodongiot
liguodongiot
llm-action

ๆœฌ้กน็›ฎๆ—จๅœจๅˆ†ไบซๅคงๆจกๅž‹็›ธๅ…ณๆŠ€ๆœฏๅŽŸ็†ไปฅๅŠๅฎžๆˆ˜็ป้ชŒ๏ผˆๅคงๆจกๅž‹ๅทฅ็จ‹ๅŒ–ใ€ๅคงๆจกๅž‹ๅบ”็”จ่ฝๅœฐ๏ผ‰

Score
100
โ˜… 24.7k โ‘‚ 2.8k +31/day
HTML
Lightning-AI
Lightning-AI
litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Score
90
โ˜… 13.5k โ‘‚ 1.5k +6/day
Python
bentoml
bentoml
OpenLLM

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Score
80
โ˜… 12.4k โ‘‚ 822 +6/day
Python
mistralai
mistralai
mistral-inference

Official inference library for Mistral models

Score
98
โ˜… 10.8k โ‘‚ 1.1k โ€”
Jupyter Notebook
openvinotoolkit
openvinotoolkit
openvino

OpenVINOโ„ข is an open source toolkit for optimizing and deploying AI inference

Score
99
โ˜… 10.5k โ‘‚ 3.3k +18/day
C++
Tiiny-AI
Tiiny-AI
PowerInfer

High-speed Large Language Model Serving for Local Deployment

Score
97
โ˜… 9.6k โ‘‚ 585 +9/day
C++
bentoml
bentoml
BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Score
70
โ˜… 8.7k โ‘‚ 981 +7/day
Python
InternLM
InternLM
lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Score
60
โ˜… 7.9k โ‘‚ 703 +5/day
Python
ai-dynamo
ai-dynamo
dynamo

A Datacenter Scale Distributed Inference Serving Framework

Score
100
โ˜… 7.5k โ‘‚ 1.3k +2/day
Rust
katanemo
katanemo
plano

Plano is an AI-native proxy and data plane for agentic apps โ€” with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.

Score
89
โ˜… 6.7k โ‘‚ 444 +71/day
Rust
algorithmicsuperintelligence
algorithmicsuperintelligence
openevolve

Open-source implementation of AlphaEvolve

Score
50
โ˜… 6.7k โ‘‚ 1.1k +45/day
Python
flashinfer-ai
flashinfer-ai
flashinfer

FlashInfer: Kernel Library for LLM Serving

Score
40
โ˜… 5.9k โ‘‚ 1.1k +6/day
Python
kserve
kserve
kserve

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

Score
80
โ˜… 5.7k โ‘‚ 1.6k +2/day
Go
Michael-A-Kuykendall
Michael-A-Kuykendall
shimmy

โšก Pure-Rust WebGPU inference engine โ€” OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Score
78
โ˜… 5.6k โ‘‚ 541 +7/day
Rust
cactus-compute
cactus-compute
cactus

Low-latency AI engine for mobile devices & wearables

Score
100
โ˜… 5.4k โ‘‚ 435 +7/day
C++
xlite-dev
xlite-dev
Awesome-LLM-Inference

๐Ÿ“šA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐ŸŽ‰

Score
30
โ˜… 5.4k โ‘‚ 420 +19/day
Python
superduper-io
superduper-io
superduper

Superduper: End-to-end framework for building custom AI applications and agents.

Score
20
โ˜… 5.3k โ‘‚ 542 +2/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
97
โ˜… 5.3k โ‘‚ 567 โ€”
Python
FellouAI
FellouAI
eko

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

Score
92
โ˜… 4.9k โ‘‚ 440 +1/day
TypeScript
lemonade-sdk
lemonade-sdk
lemonade

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

Score
96
โ˜… 4.8k โ‘‚ 389 +22/day
C++
ruvnet
ruvnet
RuVector

RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.

Score
67
โ˜… 4.3k โ‘‚ 570 +2/day
Rust
algorithmicsuperintelligence
algorithmicsuperintelligence
optillm

Optimizing inference proxy for LLMs

Score
94
โ˜… 4.2k โ‘‚ 368 +6/day
Python
NVIDIA
NVIDIA
GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Score
95
โ˜… 4.1k โ‘‚ 1.1k +9/day
Jupyter Notebook
predibase
predibase
lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Score
93
โ˜… 3.8k โ‘‚ 323 +2/day
Python
neuralmagic
neuralmagic
deepsparse

Sparsity-aware deep learning inference runtime for CPUs

Score
80
โ˜… 3.2k โ‘‚ 191 โ€”
Python
spiceai
spiceai
spiceai

A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents.

Score
56
โ˜… 3.0k โ‘‚ 210 +3/day
Rust
b4rtaz
b4rtaz
distributed-llama

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

Score
91
โ˜… 3.0k โ‘‚ 238 +7/day
C++
FasterDecoding
FasterDecoding
Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Score
63
โ˜… 2.8k โ‘‚ 204 +1/day
Jupyter Notebook
Nano-Collective
Nano-Collective
nanocoder

An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.

Score
91
โ˜… 2.2k โ‘‚ 211 โ€”
TypeScript
intel
intel
intel-extension-for-transformers

โšก Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platformsโšก

Score
58
โ˜… 2.2k โ‘‚ 216 โ€”
Python
microsoft
microsoft
aici

AICI: Prompts as (Wasm) Programs

Score
11
โ˜… 2.1k โ‘‚ 84 โ€”
Rust
neuron-core
neuron-core
neuron-ai

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that can interact with your data.

Score
90
โ˜… 2.0k โ‘‚ 227 +8/day
PHP
liltom-eth
liltom-eth
llama2-webui

Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Use `llama2-wrapper` as your local llama2 backend for Generative Agents/Apps.

Score
56
โ˜… 1.9k โ‘‚ 202 โ€”
Jupyter Notebook
beam-cloud
beam-cloud
beta9

Ultrafast serverless GPU inference, sandboxes, and background jobs

Score
89
โ˜… 1.7k โ‘‚ 145 โ€”
Go
software-mansion
software-mansion
react-native-executorch

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

Score
100
โ˜… 1.6k โ‘‚ 84 +8/day
C++
sauravpanda
sauravpanda
BrowserAI

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

Score
88
โ˜… 1.4k โ‘‚ 138 โ€”
TypeScript
felladrin
felladrin
awesome-ai-web-search

List of software that allows searching the web with the assistance of AI: https://hf.co/spaces/felladrin/awesome-ai-web-search

Score
87
โ˜… 1.4k โ‘‚ 114 +6/day
HTML
taielab
taielab
awesome-hacking-lists

A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains. Join us to explore, contribute, and enhance your hacking toolkit!

Score
100
โ˜… 1.4k โ‘‚ 264 +5/day
lean-dojo
lean-dojo
LeanCopilot

LLMs as Copilots for Theorem Proving in Lean

Score
86
โ˜… 1.3k โ‘‚ 126 +2/day
C++
character-ai
character-ai
prompt-poet

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

Score
79
โ˜… 1.1k โ‘‚ 95 โ€”
Python
ovg-project
ovg-project
kvcached

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

Score
85
โ˜… 1.1k โ‘‚ 122 +1/day
Python
AtomicBot-ai
AtomicBot-ai
Atomic-Chat

Local AI app and inference engine for agents. Run open-weight LLMs locally โ€” private, 100% offline on your computer.

Score
85
โ˜… 1.1k โ‘‚ 110 +17/day
TypeScript
dalisoft
dalisoft
awesome-hosting

List of awesome hosting sorted by minimal plan price

Score
84
โ˜… 907 โ‘‚ 92 +4/day
foldl
foldl
chatllm.cpp

Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)

Score
82
โ˜… 905 โ‘‚ 70 +3/day
C++
zhihu
zhihu
ZhiLight

A highly optimized LLM inference acceleration engine for Llama and its variants.

Score
78
โ˜… 905 โ‘‚ 102 โ€”
C++
harleyszhang
harleyszhang
llm_note

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

Score
81
โ˜… 882 โ‘‚ 88 โ€”
Python
jmaczan
jmaczan
tiny-vllm

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

Score
80
โ˜… 882 โ‘‚ 61 +51/day
C++
eastriverlee
eastriverlee
LLM.swift

LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.

Score
50
โ˜… 865 โ‘‚ 121 โ€”
C++
tingaicompass
tingaicompass
AI-Compass

โ€œAI-Compassโ€ๅฐ†ไธบ็คพๅŒบๆŒ‡ๅผ•ๅœจ AI ๆŠ€ๆœฏๆตทๆด‹ไธญ่ˆช่กŒ็š„ๆ–นๅ‘๏ผŒๆ— ่ฎบไฝ ๆ˜ฏๅˆๅญฆ่€…่ฟ˜ๆ˜ฏ่ฟ›้˜ถๅผ€ๅ‘่€…๏ผŒ้ƒฝ่ƒฝๅœจ่ฟ™้‡Œๆ‰พๅˆฐ้€šๅพ€ AI ๅ„ๅคงๆ–นๅ‘็š„่ทฏๅพ„ใ€‚ๆ—จๅœจๅธฎๅŠฉๅผ€ๅ‘่€…็ณป็ปŸๆ€งๅœฐไบ†่งฃ AI ็š„ๆ ธๅฟƒๆฆ‚ๅฟตใ€ไธปๆตๆŠ€ๆœฏใ€ๅ‰ๆฒฟ่ถ‹ๅŠฟ๏ผŒๅนถ้€š่ฟ‡ๅฎž่ทตๆŽŒๆกไปŽ็†่ฎบๅˆฐ่ฝๅœฐ็š„ๅ…จ่ฟ‡็จ‹ใ€‚

Score
83
โ˜… 844 โ‘‚ 109 +10/day
Python
mukel
mukel
llama3.java

Llama 3+ inference in pure Java

Score
79
โ˜… 813 โ‘‚ 94 โ€”
Java
stanford-mast
stanford-mast
blast

Open-source VMs-as-a-service

Score
10
โ˜… 778 โ‘‚ 50 +2/day
Python
kubernetes-sigs
kubernetes-sigs
lws

LeaderWorkerSet: An API for deploying a group of pods as a unit of replication

Score
60
โ˜… 753 โ‘‚ 159 +4/day
Go
stoyan-stoyanov
stoyan-stoyanov
llmflows

LLMFlows - Simple, Explicit and Transparent LLM Apps

Score
42
โ˜… 705 โ‘‚ 35 โ€”
Python
run-ai
run-ai
genv

GPU environment and cluster management with LLM support

Score
100
โ˜… 660 โ‘‚ 44 +1/day
Python
andrewkchan
andrewkchan
yalm

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

Score
51
โ˜… 591 โ‘‚ 64 โ€”
C++
Avarok-Cybersecurity
Avarok-Cybersecurity
atlas

Pure Rust Inference Engine

Score
44
โ˜… 585 โ‘‚ 83 +25/day
Rust
devflowinc
devflowinc
uzi

CLI for running large numbers of coding agents in parallel with git worktrees

Score
20
โ˜… 578 โ‘‚ 26 โ€”
Go
rohan-paul
rohan-paul
LLM-FineTuning-Large-Language-Models

LLM (Large Language Model) FineTuning

Score
44
โ˜… 576 โ‘‚ 140 โ€”
Jupyter Notebook
Related Topics
#llm#ai#llm-serving#llama#machine-learning#llmops#llms#large-language-models#pytorch#vllm#cuda#inference

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly