Skip to main content
Back to top
Ctrl
+
K
Search
Ctrl
+
K
Getting Started
Quickstart
Installation
Tutorials
Single XPU (Qwen3-8B)
Single XPU (Qwen3-VL-32B)
Single XPU (InternVL2_5-26B)
Multi XPU (Qwen2.5-VL-32B)
Multi XPU (GLM-4.5)
Multi XPU (Qwen3-Coder-480B-A35B(W8A8))
Multi XPU (DeepSeek-V3.2-Exp-w8a8)
Multi XPU (GLM-5-W8A8-INT8)
FAQs
User Guide
Features and Models
Supported Models
Supported Features
Configuration Guide
Environment Variables
Feature Guide
Graph Mode Guide
Quantization Guide
LoRA Adapters Guide
Release Notes
Developer Guide
Contributing
Contributing
Feature Guide
Kunlun Graph
Accuracy
Accuracy
Overall accuracy test
Operator accuracy test
Accuracy Report
Qwen2.5-VL-7B-Instruct
InternVL3_5-30B-A3B
GLM-4.5
GLM-Air-4.5
Performance
Performance_benchmark
vLLM server performance
Operator performance
Profiling
Community
Governance
Maintainers and Acknowledgments
Versioning policy
User stories
Repository
Suggest edit
.md
.pdf
Performance
Performance
#
Performance
Performance_benchmark
