Reduce large model context to 128K

docs/LLM/eemin-rocmi4-mtp.md

@@ -112,7 +112,7 @@ path's greedy decisions; it does not remove the W4A4 activation approximation.
 
 ### Serving settings
 
-- 196608 context (64K below the native 262144 maximum), 1 slot, f16 KV,
+- 131072 context (128K below the native 262144 maximum), 1 slot, f16 KV,
   context checkpoints, prompt cache. The lower limit leaves headroom for the
   model plus KV cache in the host's unified-memory budget. Concurrent requests
   queue; the server never preempts a running generation.