Skip to main content
Back to top
Ctrl
+
K
Search
Ctrl
+
K
Search
Ctrl
+
K
Search
Ctrl
+
K
Get Started
Quick Start
Usage Guide
Customization Guide
Agentic RL Training Roadmap
FAQ
Dense
Qwen3-4B with 8xH100
GLM4-9B with 8xH100
MoE
GLM-4.7-Flash with 8×H100
Qwen3-30B-A3B with 8xH100
GLM-5.2 744B-A40B with 256xH100
GLM-4.7 with 64xH100
DeepSeek R1 with 128xH100
Advanced Features
On-Policy Distillation
Speculative Decoding
Collect target features for an external draft
Low Precision Training and Rollout
Reproducibility
Fault Tolerance
Observability
PD Disaggregation
External Rollout Engines Roadmap
Delta Weight Sync
vLLM Config: Advanced Engine Deployment
Megatron Config: Role-Based Training Overrides
Supporting Model Architectures Beyond Megatron-LM
Other Usage
SFT Qwen3-4B-Base
Fully-Async Rollout Example
Multi-Agent RL
Coding-Agent RL
Developer Guide
CI (Continuous Integration)
Debugging
Trace Viewer
Profiling
Hardware Platforms
Quick Start
Repository
Open issue
System Settings
Light
Dark
Index
