Skip to content

qwen4exp: direct reads for the lazy PLE table (>2x prefill performance improvement on GB10) - #28136

Open
coder543 wants to merge 2 commits into
ggml-org:masterfrom
coder543:master
Open

qwen4exp: direct reads for the lazy PLE table (>2x prefill performance improvement on GB10)#28136
coder543 wants to merge 2 commits into
ggml-org:masterfrom
coder543:master

lazy: share the direct-read machinery, support gemma4 PLE tables

c6a9e5c
Select commit
Loading
Failed to load commit list.
Sign in for the full log view