エントリーの編集は全ユーザーに共通の機能です。
必ずガイドラインを一読の上ご利用ください。
ここにツイート内容が記載されます https://b.hatena.ne.jp/URLはspanで囲んでください
Twitterで共有ONにすると、次回以降このダイアログを飛ばしてTwitterに遷移します
You can now train OpenAI gpt-oss with RL and GRPO via Unsloth. Unsloth now offers the fastest inf... You can now train OpenAI gpt-oss with RL and GRPO via Unsloth. Unsloth now offers the fastest inference (3x faster), lowest VRAM usage (50% less) and longest context (8x longer) for gpt-oss RL vs. any implementation - with no accuracy degradation. Since reinforcement learning (RL) on gpt-oss isn't yet vLLM compatible, we had to rewrite the inference code from Transf ormers code to deliver 3x faster