master

ascend-robotfeat: mxfp8-32x32 quant

65d7fe96创建于 7 天前历史提交

文件	最后提交记录	最后更新时间
__init__.py	!2112 MindSpeed L0 reconstruction Merge pull request !2112 from Jializheng/master	1 年前
megatron_basic.py	Fix MLATransformerConfig patch Co-authored-by: JialiZheng<jializheng@huawei.com> # message auto-generated for no-merge-commit merge: !3300 merge master into master Fix MLATransformerConfig patch Created-by: JialiZheng1 Commit-by: JialiZheng Merged-by: ascend-robot Description: What this PR does / why we need it? Fix MLATransformerConfig patch Does this PR introduce any user-facing change? No How was this patch tested? Yes, it passed the deepseek_mla.sh test. See merge request: Ascend/MindSpeed!3300	2 个月前
requirements_basic.py	fix: fix torch compile patch Co-authored-by: YE ZHENYUAN<yezhenyuan@huawei.com> # message auto-generated for no-merge-commit merge: merge master0918_1 into master fix: fix torch compile patch Created-by: ryanyeee Commit-by: YE ZHENYUAN Merged-by: ascend-robot Description: fix: fix torch compile patch See merge request: Ascend/MindSpeed!2849	8 个月前
transformer_engine_basic.py	feat: mxfp8-32x32 quant Co-authored-by: kyle_zhangchi<zhangchi158@huawei.com> # message auto-generated for no-merge-commit merge: !3471 merge feat_mxfp8-32x32 into master feat: mxfp8-32x32 quant Created-by: kyle_zhangchi Commit-by: kyle_zhangchi Merged-by: ascend-robot Description: ## What this PR does / why we need it? 在Megatron框架下新增mxfp8-32x32量化算子，降低权重显存占用 ## Does this PR introduce *any* user-facing change? --fp8-recipe新增mxfp8-32x32选项 https://gitcode.com/Ascend/MindSpeed/commit/e065cbca6873bfc02661d088b07d90224333e87d?ref=feat_mxfp8-32x32&prId=3471 ## How was this patch tested? 验证文档 https://wiki.huawei.com/domains/170864/wiki/367830/WIKI2026051111046509 See merge request: Ascend/MindSpeed!3471	7 天前