| master readme文档修改 Co-authored-by: xiazhahe<nieshiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !710 merge master into master master readme文档修改 Created-by: xiazhahe Commit-by: xiazhahe Merged-by: ascend-robot Description: master readme文档修改 See merge request: Ascend/MindSpeed-RL!710 | 10 个月前 |
| 补充特性资料以及相应链接 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !835 merge master into master 补充特性资料以及相应链接 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: 补充特性相应的链接和介绍。 BF16参数副本复用 激活函数重计算 swap optimizer swap attention See merge request: Ascend/MindSpeed-RL!835 | 8 个月前 |
| 补充特性资料以及相应链接 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !835 merge master into master 补充特性资料以及相应链接 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: 补充特性相应的链接和介绍。 BF16参数副本复用 激活函数重计算 swap optimizer swap attention See merge request: Ascend/MindSpeed-RL!835 | 8 个月前 |
| fix cp bug Co-authored-by: fh_188<fenghui32@huawei.com> # message auto-generated for no-merge-commit merge: !780 merge master_cp into master fix cp bug Created-by: weixin_44917616 Commit-by: fh_188 Merged-by: ascend-robot Description: 对应ms-llm修改,fix cp bug reset_position_ids替换成reset_attention_mask variable_seq_lengths替换成 no_pad_to_seq_lengths 结果对比 https://wiki.huawei.com/domains/142209/wiki/306738/WIKI202512029261035 See merge request: Ascend/MindSpeed-RL!780 | 8 个月前 |
| master readme文档修改 Co-authored-by: xiazhahe<nieshiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !710 merge master into master master readme文档修改 Created-by: xiazhahe Commit-by: xiazhahe Merged-by: ascend-robot Description: master readme文档修改 See merge request: Ascend/MindSpeed-RL!710 | 10 个月前 |
| 完善确定性计算文档说明 master Co-authored-by: Hcm03<chengminhua1@huawei.com> # message auto-generated for no-merge-commit merge: !777 merge master into master 完善确定性计算文档说明 master Created-by: Hcm03 Commit-by: Hcm03 Merged-by: ascend-robot Description: 完善确定性计算文档说明 master See merge request: Ascend/MindSpeed-RL!777 | 8 个月前 |
| 1.增加grpo-lora readme Co-authored-by: vincent_yh<dongyunhao3@huawei.com> # message auto-generated for no-merge-commit merge: !752 merge rl-master-grpo-readme into master 1.增加grpo-lora readme Created-by: vincent_yh Commit-by: vincent_yh Merged-by: ascend-robot Description: 1.增加grpo-lora readme See merge request: Ascend/MindSpeed-RL!752 | 9 个月前 |
| [mindspeed-rl] grpo与ppo算法配置说明readme优化 Co-authored-by: psyloy<15966303071@163.com> # message auto-generated for no-merge-commit merge: !786 merge master into master [mindspeed-rl] grpo与ppo算法配置说明readme优化 Created-by: McFlurry100 Commit-by: psyloy Merged-by: ascend-robot Description: grpo与ppo算法配置说明readme优化 See merge request: Ascend/MindSpeed-RL!786 | 8 个月前 |
| master readme文档修改 Co-authored-by: xiazhahe<nieshiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !710 merge master into master master readme文档修改 Created-by: xiazhahe Commit-by: xiazhahe Merged-by: ascend-robot Description: master readme文档修改 See merge request: Ascend/MindSpeed-RL!710 | 10 个月前 |
| [mindspeed-rl] grpo与ppo算法配置说明readme优化 Co-authored-by: psyloy<15966303071@163.com> # message auto-generated for no-merge-commit merge: !786 merge master into master [mindspeed-rl] grpo与ppo算法配置说明readme优化 Created-by: McFlurry100 Commit-by: psyloy Merged-by: ascend-robot Description: grpo与ppo算法配置说明readme优化 See merge request: Ascend/MindSpeed-RL!786 | 8 个月前 |
| !558 fix dpo Merge pull request !558 from yanzhixiao/fix-dpo | 1 年前 |
| MSRL update vllm011 Co-authored-by: xiecheng_1<xiecheng22@h-partners.com> # message auto-generated for no-merge-commit merge: !783 merge master into master MSRL update vllm011 Created-by: xiecheng_1 Commit-by: xiecheng_1 Merged-by: ascend-robot Description: 1. 迭代vllm版本至011,PTA版本至271 https://wiki.huawei.com/domains/98166/wiki/300770/WIKI202511179050947 2. 移除仓库MM models 3. 修复 + 移除仓库暂不触发的相关ut See merge request: Ascend/MindSpeed-RL!783 | 8 个月前 |
| 支持search tool Co-authored-by: pengnuoheng<pengnuoheng@huawei.com> # message auto-generated for no-merge-commit merge: !846 merge master into master 支持search tool Created-by: pengnuoheng Commit-by: pengnuoheng Merged-by: ascend-robot Description: 支持search tool 自验报告:https://wiki.huawei.com/domains/127887/wiki/246533/WIKI202512179456276 See merge request: Ascend/MindSpeed-RL!846 | 8 个月前 |
| 更新资料 - VPP和partial rollout同时会卡住的问题 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !803 merge master into master 更新资料 - VPP和partial rollout同时会卡住的问题 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: update docs - vpp and partial rollout issue See merge request: Ascend/MindSpeed-RL!803 | 8 个月前 |
| [mindspeed-rl] grpo与ppo算法配置说明readme优化 Co-authored-by: psyloy<15966303071@163.com> # message auto-generated for no-merge-commit merge: !786 merge master into master [mindspeed-rl] grpo与ppo算法配置说明readme优化 Created-by: McFlurry100 Commit-by: psyloy Merged-by: ascend-robot Description: grpo与ppo算法配置说明readme优化 See merge request: Ascend/MindSpeed-RL!786 | 8 个月前 |
| mindspeed-rl profiler support multi-stage && add ppo model doc Co-authored-by: xieanran<694099604@qq.com> # message auto-generated for no-merge-commit merge: !796 merge master into master mindspeed-rl profiler support multi-stage && add ppo model doc Created-by: SoraAzzz Commit-by: xieanran Merged-by: ascend-robot Description: mindspeed-rl profiler support multi-stage && add ppo model doc profiling配置如图  profiling采集数据截图  See merge request: Ascend/MindSpeed-RL!796 | 8 个月前 |
| fix cp bug Co-authored-by: fh_188<fenghui32@huawei.com> # message auto-generated for no-merge-commit merge: !780 merge master_cp into master fix cp bug Created-by: weixin_44917616 Commit-by: fh_188 Merged-by: ascend-robot Description: 对应ms-llm修改,fix cp bug reset_position_ids替换成reset_attention_mask variable_seq_lengths替换成 no_pad_to_seq_lengths 结果对比 https://wiki.huawei.com/domains/142209/wiki/306738/WIKI202512029261035 See merge request: Ascend/MindSpeed-RL!780 | 8 个月前 |
| master readme文档修改 Co-authored-by: xiazhahe<nieshiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !710 merge master into master master readme文档修改 Created-by: xiazhahe Commit-by: xiazhahe Merged-by: ascend-robot Description: master readme文档修改 See merge request: Ascend/MindSpeed-RL!710 | 10 个月前 |
| 补充特性资料以及相应链接 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !835 merge master into master 补充特性资料以及相应链接 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: 补充特性相应的链接和介绍。 BF16参数副本复用 激活函数重计算 swap optimizer swap attention See merge request: Ascend/MindSpeed-RL!835 | 8 个月前 |
| [mindspeed-rl] grpo与ppo算法配置说明readme优化 Co-authored-by: psyloy<15966303071@163.com> # message auto-generated for no-merge-commit merge: !786 merge master into master [mindspeed-rl] grpo与ppo算法配置说明readme优化 Created-by: McFlurry100 Commit-by: psyloy Merged-by: ascend-robot Description: grpo与ppo算法配置说明readme优化 See merge request: Ascend/MindSpeed-RL!786 | 8 个月前 |
| 补充特性资料以及相应链接 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !835 merge master into master 补充特性资料以及相应链接 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: 补充特性相应的链接和介绍。 BF16参数副本复用 激活函数重计算 swap optimizer swap attention See merge request: Ascend/MindSpeed-RL!835 | 8 个月前 |
| 补充特性资料以及相应链接 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !835 merge master into master 补充特性资料以及相应链接 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: 补充特性相应的链接和介绍。 BF16参数副本复用 激活函数重计算 swap optimizer swap attention See merge request: Ascend/MindSpeed-RL!835 | 8 个月前 |