BSD Ports

misc/py-vllm 0.20.2_1 FreeBSD

High-throughput and memory-efficient LLM inference engine

System
FreeBSD
Repository
FreeBSD ports
Maintainer
[email protected]
Last update
Commit
0c4806a527
License
APACHE20
Categories
misc, python

Description

vLLM is a fast and easy-to-use library for LLM inference and serving. It provides high-throughput and memory-efficient inference for large language models (LLMs) using state-of-the-art serving technologies including:

  • PagedAttention for efficient KV cache memory management
  • Continuous batching of incoming requests
  • Optimized CUDA kernels (on supported platforms)
  • Hugging Face model compatibility
  • Various decoding algorithms including parallel sampling and beam search
  • OpenAI-compatible API server

On FreeBSD, vLLM runs in CPU/empty device mode (VLLM_TARGET_DEVICE=empty), providing pure Python inference without GPU acceleration.

Install

Binary package:

pkg install py312-vllm

From the ports tree:

cd /usr/ports/misc/py-vllm/ && make install clean

To depend on this port in another port's Makefile:

RUN_DEPENDS=	py312-vllm>0:misc/py-vllm

Packages

The version each package repository carries. “-” means the repository builds no package of it, “n/a” that there is no such repository.

Repositoryaarch64amd64armv6armv7i386
FreeBSD:14:latest-0.20.2_1---
FreeBSD:14:quarterly-0.20.2_1n/a--
FreeBSD:15:latest-0.20.2_1n/a--
FreeBSD:15:quarterly-0.20.2_1n/an/an/a
FreeBSD:16:latest--n/an/an/a
FreeBSD:16:quarterlyn/an/an/an/an/a

Dependencies

As this port's Makefile names them.

Build 8

Library 2

Runtime 62

Test 5

The full lists below include those, and their dependencies in turn.

Build dependencies 215

The first 100 are listed.

Run dependencies 553

The first 100 are listed.

Required by 1

Configuration

No options to configure.

USES
cmake:indirect python
Service scripts
none

Files

distinfo 2
FileSizeSHA256
vllm-0.20.2.tar.gz3.3526607e+0758809377798c5335c6e2fe30092abda54d9200b5b8a717b3735a63f5daa0e383
v3.10.tar.gz1.3507701e+07ba5834a1fdbb6d1c1b1c065dfd789438e7aa42c03fc52d92c02af85d78d1c75c
Master sites 2
  • PYPI
  • https://github.com/uxlfoundation/oneDNN/archive/refs/tags/:onednn_src

Commit history 2

DateCommitCreditsLog message
0c4806a527 Yuri Victorovich misc/py-vllm: fix build with the latest pytorch
9845f5db55 Yuri Victorovich sysutils/py-py-cpuinfo: remove in favor of sysutils/py-py-cpuinfo2