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 · #moe · 6 个仓库 · 按 star 排序repos · by stars

1
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
2
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
3
Python★ 16,105⑂ 1,803👁 55● 5,253⑃ 4,364▤ 108
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
★ 16,105
4
Python★ 15,079⑂ 2,936👁 119● 4,252⑃ 17,811▤ 96
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
★ 15,079
5
C★ 12,133⑂ 1,876👁 105● 19⑃ 96▤ 4
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
★ 12,133
6
Cuda★ 1,000⑂ 338👁 18● 441⑃ 2,173▤ 111
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
★ 1,000
当月每日飙升 Top10 摘要

年度月度榜入口