Skip to content

[ROCm]: fix: reduce MoE temp memory — embedding cap, weight sum default, skip trivial specs (PR3)#4193

Open
cj401-amd wants to merge 4 commits into
AI-Hypercomputer:mainfrom
cj401-amd:cj/tmem-fixes-clean-3-moe-tmem
Open

[ROCm]: fix: reduce MoE temp memory — embedding cap, weight sum default, skip trivial specs (PR3)#4193
cj401-amd wants to merge 4 commits into
AI-Hypercomputer:mainfrom
cj401-amd:cj/tmem-fixes-clean-3-moe-tmem

fix: MoE tmem reduction — megablox 9-tuple tiling, float32_weight_sum…

0ed140e
Select commit
Loading
Failed to load commit list.
Codecov / codecov/patch succeeded Jun 18, 2026 in 0s

52.94% of diff hit (target 51.15%)

View this Pull Request on Codecov

52.94% of diff hit (target 51.15%)

View more details on Codecov