Reinforcement learning for text generation on MLX (Apple Silicon)
-
Updated
Feb 15, 2026 - Python
#
gspo
Here are 3 public repositories matching this topic...
Rust-native inference runtime for Qwen3 / Qwen3.5 — OpenAI-compatible serving + integrated agent, train, and self-evolution workflows. CUDA + Metal, no PyTorch on the hot path.
agent rust metal cuda inference infra rl mlx kv-cache llm gspo flashinfer openai-compatible qwen3 qwen35
-
Updated
May 18, 2026 - Rust
OPSG-based test refinement for Java: Stable RL approach to generate maintainable, high-quality unit tests with 98.6% compilation success.
-
Updated
Jan 11, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the gspo topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gspo topic, visit your repo's landing page and select "manage topics."