Skip to content

Fix: respect --max_seq_len for sliding window models with custom kv cache + sdpa#219

Open
rhn19 wants to merge 1 commit intohuggingface:mainfrom
rhn19:fix/max-seq-len-sliding-window-ring-cache
Open

Fix: respect --max_seq_len for sliding window models with custom kv cache + sdpa#219
rhn19 wants to merge 1 commit intohuggingface:mainfrom
rhn19:fix/max-seq-len-sliding-window-ring-cache

Commits