1.vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
+8,314 stars
from 87,764 · score 9.03
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
13 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+7,287 stars
from 31,061 · score 8.89
3.SYSTRAN / faster-whisper
Faster Whisper transcription with CTranslate2
+1,752 stars
from 24,622 · score 7.47
4.GeeeekExplorer / nano-vllm
Nano vLLM
+1,516 stars
from 14,737 · score 7.32
5.LMCache / LMCache
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
+1,324 stars
from 10,932 · score 7.19
6.stas00 / ml-engineering
Machine Learning Engineering Open Book
+1,211 stars
from 18,433 · score 7.10
7.ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
+653 stars
from 57,594 · score 6.48
8.deepspeedai / DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
+541 stars
from 42,740 · score 6.30
9.triton-inference-server / server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
+241 stars
from 10,881 · score 5.49
10.hpcaitech / ColossalAI
Making large AI models cheaper, faster and more accessible
+121 stars
from 41,312 · score 4.80
11.ultralytics / yolov3
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
+65 stars
from 10,566 · score 4.19
12.superduper-io / superduper
Superduper: End-to-end framework for building custom AI applications and agents.
+33 stars
from 5,295 · score 3.53
13.huggingface / text-generation-inferenceArchived
Large Language Model Text Generation Inference
+23 stars
from 10,859 · score 3.18