1.vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
+593 stars
from 95,485 · score 6.39
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
18 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.FlashML-org / FreeVideo
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
+241 stars
from 2,332 · score 5.49
3.SYSTRAN / faster-whisper
Faster Whisper transcription with CTranslate2
+240 stars
from 26,134 · score 5.48
4.sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+192 stars
from 38,156 · score 5.26
5.fudan-generative-vision / Remory
Remory: Learning Residual Memory for Context Compaction
+151 stars
from 490 · score 5.02
6.ekzhang / resin
🧱 Experimental library for building inference engines
+132 stars
from 230 · score 4.89
7.GeeeekExplorer / nano-vllm
Nano vLLM
+128 stars
from 16,125 · score 4.86
8.LMCache / LMCache
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
+92 stars
from 12,164 · score 4.53
9.StartLuxLabs / StartLux-Decision
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
+74 stars
from 1,558 · score 4.32
10.Human-Agent-Society / reef
Infrastructure for continually self‑improving agents
+59 stars
from 7,727 · score 4.09
11.stas00 / ml-engineering
Machine Learning Engineering Open Book
+55 stars
from 19,589 · score 4.03
12.TrenTorch / TrenTorch
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
+51 stars
from 713 · score 3.95
13.ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
+26 stars
from 58,221 · score 3.30
14.triton-inference-server / server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
+10 stars
from 11,112 · score 2.40
15.deepspeedai / DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
+8 stars
from 43,273 · score 2.20
16.ultralytics / yolov3
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
+7 stars
from 10,624 · score 2.08
17.hpcaitech / ColossalAI
Making large AI models cheaper, faster and more accessible
+3 stars
from 41,430 · score 1.39
18.superduper-io / superduper
Superduper: End-to-end framework for building custom AI applications and agents.
+1 stars
from 5,327 · score 0.69