merge: TurboQuant KV cache types onto upstream master (MTP built-in)

2026-05-18 01:52:24 +03:00
parent 726704a160
commit b34ac655f3
72 changed files with 18946 additions and 257 deletions
@@ -886,8 +886,8 @@ private:

        int n_ctx_slot = llama_n_ctx_seq(ctx_tgt);
        if (n_ctx_slot > n_ctx_train) {
-            SRV_WRN("the slot context (%d) exceeds the training context of the model (%d) - capping\n", n_ctx_slot, n_ctx_train);
-            n_ctx_slot = n_ctx_train;
+            SRV_WRN("the slot context (%d) exceeds the training context of the model (%d) - using rope scaling to extend\n", n_ctx_slot, n_ctx_train);
+            // Do not cap: caller has configured rope scaling (--rope-scale / --rope-scaling yarn) to handle extended context.
        }

        slots.clear();