Skip to content

feat: support GLM-5.3 Flash dynamic FP8 KV cache with regression cove… - #1621

Open
blueswhen wants to merge 4 commits into
mainfrom
glm5.3_fp8kv
Open

feat: support GLM-5.3 Flash dynamic FP8 KV cache with regression cove…#1621
blueswhen wants to merge 4 commits into
mainfrom
glm5.3_fp8kv

refactor: reuse backend FP8 KV workspaces and derive query padding di…

5b8cd8b
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar