Spaces:

yzhuang
/

MixtureOfInputs

Sleeping

yzhuang commited on May 22

Commit

4891247

1 Parent(s): 314161f

update mem

Files changed (1) hide show

server.py CHANGED Viewed

@@ -21,8 +21,10 @@ def launch_vllm_server(beta=1.0):
         "Qwen/Qwen3-4B",
         "--tensor-parallel-size", "1",
         "--enforce-eager",
         "--max-seq-len-to-capture", "2048",
-        "--max-num-seqs", "1"
     ]
     subprocess.run(cmd, env=env)

         "Qwen/Qwen3-4B",
         "--tensor-parallel-size", "1",
         "--enforce-eager",
+        "--max-model-len", "2048",
         "--max-seq-len-to-capture", "2048",
+        "--max-num-seqs", "1",
+        "--port", "8000"
     ]
     subprocess.run(cmd, env=env)