Default Athena profiles to one inference slot

2026-08-30 22:11:55 +02:00
parent 014583e7f6
commit 8be1cd6a6f
4 changed files with 9 additions and 11 deletions
@@ -186,7 +186,7 @@ services:
      - --ubatch-size
      - "${MEDIUM_UBATCH_SIZE:-128}"
      - --parallel
-      - "${MEDIUM_PARALLEL_SLOTS:-2}"
+      - "${MEDIUM_PARALLEL_SLOTS:-1}"
      - --kv-unified
      - --jinja
      - --reasoning