[Bug] Issue with batch API

[dmakhervaks]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

I am running this file more or less (I substituted the URL with my model)

sglang/examples/runtime/openai_batch_chat.py

Line 33 in f3d32f8

batch_job = self.client.batches.create(

I see GPU utilization being used and in the logs, I see that the requests are actually being generated. However on my client side, the code is just stuck in this loop:

This happens in docker image 0.3.0, but works fine 0.2.7

Reproduction

Running this file:

sglang/examples/runtime/openai_batch_chat.py

Line 33 in f3d32f8

batch_job = self.client.batches.create(

Environment

Python: 3.10.14 (main, Apr 6 2024, 18:45:05) [GCC 9.4.0]
CUDA available: True
GPU 0,1,2,3,4,5,6,7: NVIDIA H100 80GB HBM3
GPU 0,1,2,3,4,5,6,7 Compute Capability: 9.0
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.1, V12.1.105
CUDA Driver Version: 550.90.07
PyTorch: 2.4.0+cu121
sglang: 0.3.0
flashinfer: 0.1.6+cu121torch2.4
triton: 3.0.0
transformers: 4.44.2
requests: 2.32.3
tqdm: 4.66.5
numpy: 1.26.4
aiohttp: 3.10.5
fastapi: 0.112.2
hf_transfer: 0.1.8
huggingface_hub: 0.24.6
interegular: 0.3.3
packaging: 24.1
PIL: 10.4.0
psutil: 6.0.0
pydantic: 2.8.2
uvicorn: 0.30.6
uvloop: 0.20.0
zmq: 26.2.0
vllm: 0.5.5
multipart: 0.0.9
openai: 1.43.0
anthropic: 0.34.1
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 NIC10 NIC11 NIC12 NIC13 NIC14 NIC15 NIC16 NIC17 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE PIX NODE NODE SYS SYS SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE PIX NODE SYS SYS SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE PIX SYS SYS SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS PIX PIX PIX NODE NODE NODE SYS SYS SYS SYS PIX NODE NODE NODE 1,3,5,7,9,11 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS NODE NODE NODE PIX NODE NODE SYS SYS SYS SYS NODE PIX NODE NODE 1,3,5,7,9,11 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS NODE NODE NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE PIX NODE 1,3,5,7,9,11 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS NODE NODE NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE PIX 1,3,5,7,9,11 1 N/A
NIC0 PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE SYS SYS SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS
NIC1 NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE SYS SYS SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS
NIC2 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE SYS SYS SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS
NIC3 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X SYS SYS SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS
NIC4 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS X PIX PIX NODE NODE NODE SYS SYS SYS SYS PIX NODE NODE NODE
NIC5 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX X PIX NODE NODE NODE SYS SYS SYS SYS PIX NODE NODE NODE
NIC6 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX PIX X NODE NODE NODE SYS SYS SYS SYS PIX NODE NODE NODE
NIC7 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS NODE NODE NODE X NODE NODE SYS SYS SYS SYS NODE PIX NODE NODE
NIC8 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE NODE NODE X NODE SYS SYS SYS SYS NODE NODE PIX NODE
NIC9 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE NODE NODE X SYS SYS SYS SYS NODE NODE NODE PIX
NIC10 PIX NODE NODE NODE SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS X NODE NODE NODE SYS SYS SYS SYS
NIC11 NODE PIX NODE NODE SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS SYS SYS NODE X NODE NODE SYS SYS SYS SYS
NIC12 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS SYS SYS NODE NODE X NODE SYS SYS SYS SYS
NIC13 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS SYS SYS NODE NODE NODE X SYS SYS SYS SYS
NIC14 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX PIX PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE
NIC15 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS NODE NODE NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE
NIC16 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE
NIC17 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X

Legend:

X = Self
SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
PIX = Connection traversing at most a single PCIe bridge
NV# = Connection traversing a bonded set of # NVLinks

NIC Legend:

NIC0: mlx5_0
NIC1: mlx5_1
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
NIC6: mlx5_6
NIC7: mlx5_7
NIC8: mlx5_8
NIC9: mlx5_9
NIC10: mlx5_10
NIC11: mlx5_11
NIC12: mlx5_12
NIC13: mlx5_13
NIC14: mlx5_14
NIC15: mlx5_15
NIC16: mlx5_16
NIC17: mlx5_17

ulimit soft: 1024

[abhilashsharma]

I am facing the same issue @dmakhervaks, were you able to find a workaround for this?

[merrymercy]

@abhilashsharma @dmakhervaks Can you provide a mini reproducible example?

[dmakhervaks]

@merrymercy This is the code i am running on the client side to send batch API to the server:

sglang/examples/runtime/openai_batch_chat.py

Line 33 in f3d32f8

batch_job = self.client.batches.create(

The server side is running docker 0.3.0