What's Changed

• Add the official AWS launch blog post and reformat the AWS section to awesome-gpt-oss.md by @neoremind in https://github.com/openai/gpt-oss/pull/197
• Metal: simplify Model type check in Python wrapper by @Maratyszcza in https://github.com/openai/gpt-oss/pull/202
• Metal: move max_batch_tokens from Model into Context by @Maratyszcza in https://github.com/openai/gpt-oss/pull/201
• GPT-OSS Reinforcement Finetuning Example by @danielhanchen in https://github.com/openai/gpt-oss/pull/208
• add stateful jupyter notebook option and make browser more reliable by @dkundel-openai in https://github.com/openai/gpt-oss/pull/199
• Removing GPU-CPU sync during MoE MLP in Prefill by @ibahmed-oai in https://github.com/openai/gpt-oss/pull/218
• Eliding copying the KV after RoPE to the KV cache during prefill by @ibahmed-oai in https://github.com/openai/gpt-oss/pull/221
• fix: remove duplicated variable causing Metal build failure by @hukurou0 in https://github.com/openai/gpt-oss/pull/220
• Add user-agent to headers for tracking by @smboy in https://github.com/openai/gpt-oss/pull/235

New Contributors

• @neoremind made their first contribution in https://github.com/openai/gpt-oss/pull/197