Wen Sun

docs: fix incorrect `docker run` options in distributed training employment chapter

3

This fix is patched to distributed training employment chapter.

Update collective ops docs

1

更新集合通信操作的中文文档，包括： - paddle.distributed.all_gather - paddle.distributed.all_reduce - paddle.distributed.alltoall - paddle.distributed.broadcast - paddle.distributed.reduce - paddle.distributed.recv - paddle.distributed.irecv - paddle.distributed.send - paddle.distributed.isend - paddle.distributed.scatter - paddle.distributed.reduce_scatter - paddle.distributed.new_group 增加集合通信操作的中文文档，包括： - paddle.distributed.destroy_process_group - paddle.distributed.alltoall_single...

Fix a spelling mistake, and add a missing line in 3-7-4.

Any plan for a larger context size?

1

A larger context size is likely to be helpful for many downstream tasks. Recently proposed researches have extended LLaMA models' context size to 8k and beyond via RoPE scaling. Do...

顺便改了一些笔误（

Reproduction Inquiry: DeepSeek-V3.1 AIME2024 & AIME2025 Results

1

Hi DeepSeek Team, First of all, thank you for open-sourcing **DeepSeek-V3.1** and sharing the impressive benchmark results. Our team has been working to reproduce the results reported in your official...