vLLM
@vllm-project • Open source projects from vllm-project. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
82%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
26 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (14), Rust (4), Unknown (4)
Average size
578
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-09-12(12h ago)GitHub API fallback30 repositories
82%
of the visible star count comes from this organization's top three repositories.
578
stars per repository in this same snapshot.
Python
is the most common language here, with 26 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 30 repositories.
Balanced portfolio across 30 reposTop 3 share 82%
Organization pages work best when you separate portfolio breadth from flagship concentration. In vLLM's case, the visible top three repositories account for about 82% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (14), Rust (4), Unknown (4). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | vllm-project/vllm-omni A framework for efficient model inference with omni-modality models | Python | 6.8K |
| 2 | vllm-project/semantic-router A programmable Mixture-of-Models router for heterogeneous LLM inference | Go | 5.8K |
| 3 | vllm-project/vllm-metal Community maintained hardware plugin for vLLM on Apple Silicon | Python | 1.7K |
| 4 | vllm-project/recipes Common recipes to run vLLM | JavaScript | 1K |
| 5 | vllm-project/vime An LLM post-training framework with vLLM for RL Scaling | Python | 458 |
| 6 | vllm-project/router A high-performance and light-weight router for vLLM large scale deployment | Rust | 403 |
| 7 | vllm-project/agentic-api Stateful API logic for agentic applications using vLLM | Rust | 260 |
| 8 | vllm-project/humming Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for quantized inference. | Python | 229 |
| 9 | vllm-project/afd-plugin vLLM plugin for attention-ffn disaggregation support | Python | 209 |
| 10 | vllm-project/vllm-skills Agent skills for vLLM | Shell | 99 |
| 11 | vllm-project/vllm-xpu-kernels The vLLM XPU kernels for Intel GPU | C++ | 70 |
| 12 | vllm-project/vllm-daily vLLM Daily Summarization of Merged PRs | 54 | |
| 13 | vllm-project/vllm-bench High-performance Rust benchmark client for vLLM serving endpoints. | Rust | 52 |
| 14 | vllm-project/vllm-neuron Community maintained hardware plugin for vLLM on AWS Neuron | Python | 51 |
| 15 | vllm-project/vllm-gguf-plugin vLLM Quantization plugin for GGUF | Python | 47 |
| 16 | vllm-project/dllm-plugin vLLM plugin for block-based diffusion language model (dLLM) support | Python | 29 |
| 17 | vllm-project/tml-fa4 FA4-based Relative Attention Kernel developed by TML and Colfax | Python | 18 |
| 18 | vllm-project/perf-eval Performance benchmark & accuracy evaluation for vLLM | Python | 17 |
| 19 | vllm-project/vllm-dashboard | TypeScript | 13 |
| 20 | vllm-project/bart-plugin vLLM Model plugin for the encoder-decoder BART model | Python | 13 |
| 21 | vllm-project/vvm Manage multiple vLLM installations with isolated Python virtual environments. Switch between releases, commits, branches, and PRs instantly. | Rust | 12 |
| 22 | vllm-project/FlashKDA | Cuda | 12 |
| 23 | vllm-project/vLLM-in-PyTorch-Conference-2025 | 11 | |
| 24 | vllm-project/perf-dashboard Performance dashboard for vLLM | Python | 5 |
| 25 | vllm-project/vllm-bnb-plugin vLLM Quantization plugin for bitsandbytes | Python | 3 |
| 26 | vllm-project/lm-evaluation-harness A framework for few-shot evaluation of language models. | 2 | |
| 27 | vllm-project/MSA | Python | 1 |
| 28 | vllm-project/vllm-docs | TypeScript | 1 |
| 29 | vllm-project/DeepGEMM DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling | Cuda | 1 |
| 30 | vllm-project/DeepSelect DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.