# jmaczan/tiny-vllm

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

Repository: https://github.com/jmaczan/tiny-vllm
Canonical: https://ross.abutalabs.com/products/tiny-vllm
Language: C++
License: Apache-2.0
License Family: permissive
Topics: ai, hpc, llm, llm-inference, vllm, tiny-vllm, cpp, cuda, pagedattention, attention, batching, course, inference
Last push: 2026-08-23T14:20:13+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 14
- inputs: {"age_days": 205, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1081, forks 84 (observed 2026-08-28T04:03:30.759389+00:00)

## What it is
tiny-vllm is both a minimal high-performance LLM inference engine written in C++ and CUDA, and a hands-on course that walks through building it from scratch. It implements a Llama 3.2 1B forward pass with CUDA kernels, KV cache, continuous batching, FlashAttention-style online softmax, and PagedAttention.

## Use cases
- learn how LLM inference engines work internally
- build a mini vLLM in C++ and CUDA
- understand PagedAttention and KV cache implementation
- study CUDA kernel engineering for transformers
- teach a university course on LLM inference systems
- implement continuous batching from scratch

## When to choose
- you want to learn inference engine internals by implementing them yourself
- you need a small readable codebase demonstrating PagedAttention and batching
- you are an educator looking for a teaching resource on GPU inference

## When to avoid
- you need a production-ready inference server for real workloads
- you want broad model support beyond Llama-style architectures
- you prefer not to write or maintain CUDA code

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, gpu-computing, machine-learning
- domain: large-language-models, deep-learning, gpu-computing, tutorials
- platform: cpp
- tags: cuda-kernels, paged-attention, kv-cache, continuous-batching, flashattention, inference-engine, course, gpu, linux

## Member repositories
- jmaczan/tiny-vllm (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:30.759389+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:22.843020+00:00, confidence not recorded.
  - readme: https://github.com/jmaczan/tiny-vllm (fetched 2026-08-28T04:03:30.759389+00:00, sha 55901a8aa146)
- Data as of 2026-08-30T08:39:29.467469+00:00.