"GET / HTTP/1.1" 404 Not Found

[LordEdison]

I try to follow your "quick start" and launch a server, with following code:

python -m sglang.launch_server --model-path mistralai/Mistral-7B-Instruct-v0.1 \
--port 30000 --host 0.0.0.0

Unfortunately I encounter some error😭

[2024-12-13 01:44:59 TP0] Load weight end. type=MistralForCausalLM, dtype=torch.bfloat16, avail mem=9.69 GB
[2024-12-13 01:44:59 TP0] Memory pool end. avail mem=2.44 GB
[2024-12-13 01:44:59 TP0] Capture cuda graph begin. This can take up to several minutes.
[2024-12-13 01:45:01 TP0] Capture cuda graph end. Time elapsed: 2.19 s
[2024-12-13 01:45:02 TP0] max_total_num_tokens=56524, max_prefill_tokens=16384, max_running_requests=2049, context_len=32768
[2024-12-13 01:45:02] INFO:     Started server process [3831493]
[2024-12-13 01:45:02] INFO:     Waiting for application startup.
[2024-12-13 01:45:02] INFO:     Application startup complete.
[2024-12-13 01:45:02] INFO:     Uvicorn running on http://0.0.0.0:30000 (Press CTRL+C to quit)
[2024-12-13 01:45:26] INFO:     127.0.0.1:40418 - "GET / HTTP/1.1" 404 Not Found
[2024-12-13 01:47:34] Initialization failed. warmup error: Traceback (most recent call last):
  File "/home/sglang/python/sglang/srt/server.py", line 621, in _wait_and_warmup
    assert res.status_code == 200, f"{res=}, {res.text=}"
AssertionError: res=<Response [502]>, res.text=''

Killed

How can I fix it? Thanks!

[zhaochenyang20]

@LordEdison Could you change your port plz? And, provide us with your environment.

[zhaochenyang20]

@LordEdison Hey. Have you tried this? We will close your issue in three days if you do not reply.