vllm and nano-vllm

The latter project, Nano vLLM, is an ecosystem sibling that appears to be a lightweight, potentially experimental or educational reimplementation of the core concepts of vLLM, as suggested by its name and significantly lower star count with no monthly downloads.

vllm
100
Verified
nano-vllm
53
Established
Maintenance 25/25
Adoption 25/25
Maturity 25/25
Community 25/25
Maintenance 6/25
Adoption 10/25
Maturity 15/25
Community 22/25
Stars: 73,007
Forks: 14,312
Downloads: 7,953,905
Commits (30d): 996
Language: Python
License: Apache-2.0
Stars: 12,189
Forks: 1,704
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Package No Dependents

About vllm

vllm-project/vllm

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

Implements PagedAttention for efficient KV cache management and continuous request batching to maximize GPU utilization. Supports multiple quantization schemes (GPTQ, AWQ, INT4/8, FP8), speculative decoding, and tensor/pipeline parallelism across NVIDIA, AMD, Intel, and TPU hardware. Provides OpenAI-compatible API endpoints and integrates directly with Hugging Face models, including multi-modal and mixture-of-expert architectures.

About nano-vllm

GeeeekExplorer/nano-vllm

Nano vLLM

Implements core vLLM optimizations—prefix caching, tensor parallelism, CUDA graphs, and torch compilation—in a minimal ~1,200-line Python codebase. Provides a vLLM-compatible API for fast offline LLM inference with demonstrated throughput matching or exceeding the full vLLM implementation. Designed for educational clarity and efficient deployment on resource-constrained hardware like consumer GPUs.

Scores updated daily from GitHub, PyPI, and npm data. How scores work