Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Documenti analoghi

• COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
  di: Xi, Haocheng, et al.
  Pubblicazione: (2024)
• Flash-KMeans: Fast and Memory-Efficient Exact K-Means
  di: Yang, Shuo, et al.
  Pubblicazione: (2026)
• Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
  di: Yang, Shuo, et al.
  Pubblicazione: (2025)
• SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
  di: Liu, Bingshuai, et al.
  Pubblicazione: (2025)
• Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  di: Xi, Haocheng, et al.
  Pubblicazione: (2025)