vllm-project /vllm

Open on GitHub

A high-throughput and memory-efficient inference and serving engine for LLMs

Stars: 96,162 stars
Forks: 24,323 forks
Language: Python
License: APACHE-2.0
Created: Feb 9, 2023
Last push: Nov 2, 2026
Updated: Nov 2, 2026

In the Repository Index from the Seed Dataset since Oct 22, 2026.

Star History

192 days recorded, Apr 26, 2026 – Nov 3, 2026 (UTC). Net change +18,831 stars.

Net stars each dayhighest +458

Apr 26, 2026Nov 3, 2026

Cumulative net stars since Apr 26, 2026+18,831

Apr 26, 2026Nov 3, 2026

Observations

What the Repository Host reported each day.

Day (UTC)	Stars	Forks	Last push	Archived
Nov 3, 2026	96,162	24,323	Nov 2, 2026	No
Nov 2, 2026	96,078	24,265	Nov 2, 2026	No
Nov 1, 2026	96,003	24,230	Oct 31, 2026	No
Oct 31, 2026	95,936	24,205	Oct 30, 2026	No
Oct 30, 2026	95,866	24,152	Oct 29, 2026	No
Oct 29, 2026	95,787	24,113	Oct 28, 2026	No
Oct 28, 2026	95,711	24,070	Oct 28, 2026	No
Oct 27, 2026	95,626	24,009	Oct 26, 2026	No
Oct 26, 2026	95,485	23,946	Oct 25, 2026	No
Oct 25, 2026	95,343	23,899	Oct 24, 2026	No
Oct 24, 2026	95,251	23,862	Oct 24, 2026	No
Oct 23, 2026	95,151	23,804	Oct 23, 2026	No
Oct 22, 2026	95,140	23,801	Oct 22, 2026	No

Attention Score

7 daysOct 27, 2026 – Nov 2, 2026
+593 stars · score 6.39
Eligible to rank on the trending page.
Trending in 7 days
30 daysOct 4, 2026 – Nov 2, 2026
+3,124 stars · score 8.05
Eligible to rank on the trending page.
Trending in 30 days
90 daysAug 5, 2026 – Nov 2, 2026
+8,314 stars · score 9.03
Eligible to rank on the trending page.
Trending in 90 days
180 daysMay 7, 2026 – Nov 2, 2026
+17,617 stars · score 9.78
Eligible to rank on the trending page.
Trending in 180 days

A repository is ranked only when its Star History covers every day of the window and its latest Observation is not missing.

Repositories with shared topics

Repositories in the index that have one or more topics in common with this repository and the same primary language (Python). Sorted by the number of shared topics, then by stars.

sgl-project/sglang38K
SGLang is a high-performance serving framework for large language models and multimodal models.
Shared topics:blackwellcudadeepseekgpt-ossinferencellamallmmoeqwentransformer
hiyouga/LlamaFactory76K
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Shared topics:deepseekgptllamallmmoeqwen
modelscope/ms-swift16K
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).
Shared topics:deepseekkimillmmoeqwenqwen3
ekzhang/resin375
🧱 Experimental library for building inference engines
Shared topics:cudadeepseekgpt-ossinferencellmllm-serving
huggingface/transformers168K
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Shared topics:deepseekllmpytorchqwentransformer
unslothai/unsloth79K
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Shared topics:deepseekllamallmopenaiqwen
NVIDIA/TensorRT-LLM15K
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.
Shared topics:blackwellcudallm-servingmoepytorch
LMCache/LMCache12K
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Shared topics:amdcudainferencellmpytorch

Report a problem with this page