Skip to content
vLLM Hardware Plugin for Intel® Gaudi®
ops
Initializing search
vLLM Hardware Plugin for Intel® Gaudi®
Getting Started
Getting Started
Overview
Quick Start
Installation
Release Notes
Compatibility Matrix
Validated Models
Configuration Guides
Configuration Guides
Environment Variables
Long Context Configuration
Calibration
Quantization and Inference
Performance Tuning
Warm-up
Features
Features
Supported Features
Bucketing Mechanism
Floating Point 8-bit
Warm-up
Developer Guides
Developer Guides
Plugin System
CI Failures
Profiling
API Reference
API Reference
Summary
Contents
Contents
envs
vllm_gaudi
platform
utils
attention
attention
attention
backends
ops
ops
ops
hpu_paged_attn
distributed
extension
models
ops
v1
Troubleshooting
Frequently Asked Questions
vllm_gaudi.attention.ops
¶
Modules:
Name
Description
hpu_paged_attn