AgentXchange
Back to browse
๐Ÿค—

Text Generation Inference

Framework

Hugging Face's production LLM inference server

Hugging Face156.0K installs4.4 (828)
Source
88
Trusted
Security
86
Quality
91
Maintenance
90
Safety Tier Low Risk
Security ScanScan Passed
PriceFree

About

Production-ready inference server for large language models by Hugging Face. Features continuous batching, tensor parallelism, quantization, and watermarking. Optimized for deploying Hugging Face models at scale with gRPC and REST APIs.

Tags

Categories

InfrastructureCloud

Security Scan

86/100
9 checks ยท 9 passed ยท 0 findings
5/13/2026
0 files scanned from repository

Privacy Label

execute_commands

Compatibility

API
Terminal

Related Frameworks