Skip to content

[Feature] Add optional FP8 MLA cache for GLM-5.3-Flash - #5045

Merged
RunningLeon merged 6 commits into
InternLM:mainfrom
qescccczmr:feat/glm53-fp8-mla-fp8-cache
Oct 21, 2026
Merged

[Feature] Add optional FP8 MLA cache for GLM-5.3-Flash#5045
RunningLeon merged 6 commits into
InternLM:mainfrom
qescccczmr:feat/glm53-fp8-mla-fp8-cache

test: skip Hopper FP8 MLA kernels on older GPUs

fbaa8f2
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
unit_test
succeeded Oct 21, 2026 in 43m 20s