Run GRPO reasoning fine-tunes at 100K+ context on a single H100 with Unsloth's new long-context batching

Unsloth Docs·low signal

Unsloth's long-context GRPO release adds batching algorithms enabling ~7x (up to 12x+) longer-context RL training with no accuracy or speed penalty versus optimized FA3/kernel/chunked-loss setups; Qwen3-8B GRPO reaches 110K context on one 80GB H100 via vLLM+QLoRA (65K for gpt-oss with BF16 LoRA). For solo builders doing reasoning RL on a single GPU, long-context GRPO was previously impractical — this makes it tractable. Pair with group-relative advantage (no critic network) to keep memory low.