feat(recipe): add MiMo-7B MTP Megatron SGLang NPU recipe - #87
Open
RordChang wants to merge 2 commits into
Open
Conversation
Signed-off-by: RordChang <13223981771@163.com>
This change was developed with assistance from OpenAI Codex. Signed-off-by: RordChang <13223981771@163.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
交付内容
verl_ascend_practice中新增 MiMo-7B-RL MTP Ascend recipe。HCCLCheckpointEngine,不新增 SGLang 专用 checkpoint engine。关联任务:#20
关键配置
下载
XiaomiMiMo/MiMo-7B-RL后,将模型config.json中的max_position_embeddings设为32768。数据目录应包含:运行方式:
cd /path/to/verl git apply /path/to/verl-ascend-recipe/verl_ascend_practice/patches/mtp_checkpoint_engine_reoffload.patch DEVICE=npu \ MODEL_PATH=/path/to/MiMo-7B-RL \ DATA_ROOT=/path/to/math \ NPUS_PER_NODE=4 \ TOTAL_TRAINING_STEPS=100 \ bash /path/to/verl-ascend-recipe/verl_ascend_practice/run_mimo_7b_mtp_megatron_npu.sh脚本允许通过环境变量调整模型、数据、并行度、batch、序列长度、MTP loss scaling、checkpoint 和日志目录,也允许在命令末尾追加 Hydra overrides。
实验结果
环境:Atlas 800T A2,4 x Ascend 910B;CANN 9.0、Python 3.11.15、torch/torch-npu 2.8、SGLang 0.5.10、Megatron Core/MindSpeed 0.16.0、MBridge 0.15.1。
完整训练日志:training_100step.log
检查
bash -n verl_ascend_practice/run_mimo_7b_mtp_megatron_npu.shgit diff --check upstream/main...HEADgit apply --check verl_ascend_practice/patches/mtp_checkpoint_engine_reoffload.patch(在 verl main 工作树执行)This contribution was developed with assistance from OpenAI Codex. The human submitter remains responsible for review and submission.
Closes #20