GitHub Trending Rank Radar

GitHub 开源项目趋势榜单 · 每日双快照 · 十一种榜单 · 日 / 月 / 年历史回看

GitHub

独立采集 · 开源数据

独立追踪 GitHub 星标的每一次脉动

每日两次快照,用差值还原真实增长——不是又一份热榜镜像。

浏览今日榜单 →
Star 范围 – k

2026-11-16 · #inference · 20 个仓库 · 按 star 排序repos · by stars

1
Python★ 96,966⑂ 24,859👁 604● 19,883⑃ 47,020▤ 109
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 96,966
2
Python★ 58,272⑂ 17,434👁 379● 9,428⑃ 3,071▤ 10
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
★ 58,272
3
C++★ 55,217⑂ 6,306👁 399● 2,007⑃ 1,565▤ 45
Port of OpenAI's Whisper model in C/C++
★ 55,217
4
Python★ 43,326⑂ 5,072👁 350● 3,518⑃ 4,614▤ 120
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
★ 43,326
5
Python★ 41,425⑂ 4,487👁 374● 1,783⑃ 4,503▤ 50
Making large AI models cheaper, faster and more accessible
★ 41,425
6
Python★ 38,901⑂ 10,510👁 185● 8,429⑃ 41,621▤ 64
SGLang is a high-performance serving framework for large language models and multimodal models.
★ 38,901
7
C++★ 37,706⑂ 6,228👁 530● 5,709⑃ 651▤ 72
Cross-platform, customizable ML solutions for live and streaming media.
★ 37,706
8
C++★ 24,052⑂ 4,551👁 566● 3,916⑃ 3,195▤ 50
ncnn is a high-performance neural network inference framework optimized for the mobile platform
★ 24,052
9
Python★ 19,717⑂ 1,303👁 156● 44⑃ 98▤ 0
Machine Learning Engineering Open Book
★ 19,717
10
Python★ 17,219⑂ 1,706👁 104● 418⑃ 491▤ 6
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
★ 17,219
11
Python★ 16,439⑂ 2,863👁 86● 112⑃ 182▤ 0
Nano vLLM
★ 16,439
12
Python★ 9,657⑂ 901👁 58● 3,012⑃ 3,079▤ 151
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
★ 9,657
13
Python★ 9,433⑂ 798👁 61● 117⑃ 2,606▤ 27
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
★ 9,433
14
C++★ 9,034⑂ 3,119👁 278● 1,864⑃ 88▤ 1
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
★ 9,034
15
Python★ 7,829⑂ 739👁 512● 415⑃ 1,033▤ 5
Infrastructure for continually self‑improving agents
★ 7,829
16
Python★ 7,104⑂ 577👁 21● 10⑃ 18▤ 4
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
★ 7,104
17
Go★ 6,479⑂ 1,122👁 61● 2,693⑃ 3,930▤ 4
An open, programmable decision layer for models and compute.
★ 6,479
18
Rust★ 3,348⑂ 240👁 23● 34⑃ 1,109▤ 38
A high-performance inference engine for AI models
★ 3,348
19
Python★ 1,793⑂ 741👁 9● 665⑃ 3,332▤ 23
High Performance Serving Runtime For Interactive Super Intelligence System
★ 1,793
20
★ 991⑂ 64👁 15● 143⑃ 1▤ 243
MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.
★ 991
当月每日飙升 Top10 摘要

年度月度榜入口