vllm-cpu
A high-throughput and memory-efficient inference and serving engine for LLMs
$
pip install vllm-cpuOfficial docs outline
Extra Credit builds an outline of vllm-cpu's docs the first time your work uses it. Until then, start at the official documentation.
More in Python packages
All 9,553-
django-multitenant Django Library to Implement Multi-tenant databases
-
mocket Socket Mock Framework - for all kinds of socket animals, web-clients included - with gevent/asyncio/SSL support
-
qwen-tts Qwen-TTS python package
-
django-rest-swagger Swagger UI for Django REST Framework 3.5+
-
ocp-tessellate Tessellate OCP (https://github.com/cadquery/OCP) objects to use with threejs
-
sfctl Azure Service Fabric command line
-
stellar-sdk The Python Stellar SDK library provides APIs to build transactions and connect to Horizon and Stellar RPC server.
-
blurhash Pure-Python implementation of the blurhash algorithm.
-
mypy-boto3-resiliencehubv2 Type annotations for boto3 ResilienceHubV2 1.43.62 service generated with mypy-boto3-builder 8.12.0
-
mailchimp3 A python client for v3 of MailChimp API
-
apple-compress Python bindings for Apple's libcompression.
-
mypy-boto3-route53domains Type annotations for boto3 Route53Domains 1.43.4 service generated with mypy-boto3-builder 8.12.0