slime
@slime_framework
The LLM post-training framework for RL Scaling.
12 Following 2K Followers
slime now adds --release-train, pushing the inference system during agentic RL training to a new limit.
In colocated RL training, we want SGLang to use as much room as possible for inference-side optimizations such as HiCache, instead of being constrained by offloaded Megatron training processes.
--release-train makes this possible by releasing the Megatron training process during rollout and reloading it for each training round.
This gives SGLang more configuration headroom in colocated RL workloads.
PR:
Show more
🚀 slime v0.3.0 is out!
This release is a major step toward agent-first RL.
We turned slime’s existing multi-turn / agentic capabilities into a more coherent foundation:
- slime/agent with reusable sandbox-agent components
- OpenAI / Anthropic-compatible adapters
- black-box coding-agent RL example
- variable global batch-size training
- fully async training as a first-class path
- lower host-memory usage for more flexible rollout-inference setups
- PPO refactor with actor-critic colocation
- delta weight sync, FlashQLA for Qwen GDN, --save-hf, and more CI coverage
slime is moving closer to a practical open-source framework for large-scale agentic RL.
Release note:
Show more
