GLM-5.3-Flash

Running on Zero

apathy-exe commited on Aug 27

Commit

0f5f17c

verified ·

1 Parent(s): a6da030

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -112,8 +112,8 @@ def start_llama_server():
         "-tb", "16",
         "-fa", "on",
         "--parallel", "1",
-        "--spec-type", "draft-mtp",
-        "--spec-draft-n-max", "4",
         "--cache-type-k", "q4_0",
         "--cache-type-v", "q4_0",
         "--jinja",

         "-tb", "16",
         "-fa", "on",
         "--parallel", "1",
+        #"--spec-type", "draft-mtp",
+        #"--spec-draft-n-max", "4",
         "--cache-type-k", "q4_0",
         "--cache-type-v", "q4_0",
         "--jinja",