Spaces:

yzhuang
/

MixtureOfInputs

Sleeping

yzhuang commited on May 22

Commit

f4cd2da

1 Parent(s): 4891247

update

Files changed (1) hide show

server.py CHANGED Viewed

@@ -24,7 +24,8 @@ def launch_vllm_server(beta=1.0):
         "--max-model-len", "2048",
         "--max-seq-len-to-capture", "2048",
         "--max-num-seqs", "1",
-        "--port", "8000"
     ]
     subprocess.run(cmd, env=env)

         "--max-model-len", "2048",
         "--max-seq-len-to-capture", "2048",
         "--max-num-seqs", "1",
+        "--port", "8000",
+        "--disable-async-output-proc"
     ]
     subprocess.run(cmd, env=env)