[Bug] Deterministic inference is not supported for Qwen3.5 next 400B FP8

[Mikechen-0105]

Checklist

• I searched related issues but found no solution.
• The bug persists in the latest version.
• Issues without environment info and a minimal reproducible demo are hard to resolve and may receive no feedback.
• If this is not a bug report but a general question, please start a discussion at https://github.com/sgl-project/sglang/discussions. Otherwise, it will be closed.
• Please use English. Otherwise, it will be closed.

Describe the bug

I launched a Qwen3.5 next 400B model with fp8 quantization, TP=8 setting, and run the
python3 -m sglang.test.test_deterministic --n-trials 50 --test-mode single test.
The results differ with batch size from 32 to 33. The output content differs in the middle

Reproduction

The server is launched with
python -m sglang.launch_server --model-path <model_path> --tensor-parallel-size 8 --attention-backend flashinfer --quantization fp8 --enable-deterministic-inference --disable-cuda-graph
Test code directly call
python3 -m sglang.test.test_deterministic --n-trials 50 --test-mode single

Environment

Python: 3.12.3 (main, Feb 4 2025, 14:48:35) [GCC 13.3.0]
CUDA available: True
GPU 0,1,2,3,4,5,6,7: NVIDIA H20-3e
GPU 0,1,2,3,4,5,6,7 Compute Capability: 9.0
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.9, V12.9.86
CUDA Driver Version: 570.133.20
PyTorch: 2.9.1+cu128
sglang: 0.5.8.post1
sgl_kernel: 0.3.21
flashinfer_python: 0.6.1
flashinfer_cubin: Module Not Found
flashinfer_jit_cache: Module Not Found
triton: 3.5.1
transformers: 4.57.1
torchao: 0.9.0
numpy: 2.4.2
aiohttp: 3.13.3
fastapi: 0.128.6
hf_transfer: 0.1.9
huggingface_hub: 0.36.2
interegular: 0.3.3
modelscope: 1.34.0
orjson: 3.11.7
outlines: 0.1.11
packaging: 26.0
psutil: 7.2.2
pydantic: 2.12.5
python-multipart: 0.0.22
pyzmq: 27.1.0
uvicorn: 0.40.0
uvloop: 0.22.1
vllm: Module Not Found
xgrammar: 0.1.27
openai: 2.6.1
tiktoken: 0.12.0
anthropic: 0.79.0
litellm: Module Not Found
decord2: 3.0.0
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX PHB SYS SYS 0-79 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 PXB PHB SYS SYS 0-79 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 PHB PIX SYS SYS 0-79 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 PHB PXB SYS SYS 0-79 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS PIX PHB 80-159 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS PXB PHB 80-159 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS PHB PIX 80-159 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS PHB PXB 80-159 1 N/A
NIC0 PIX PXB PHB PHB SYS SYS SYS SYS X PHB SYS SYS
NIC1 PHB PHB PIX PXB SYS SYS SYS SYS PHB X SYS SYS
NIC2 SYS SYS SYS SYS PIX PXB PHB PHB SYS SYS X PHB
NIC3 SYS SYS SYS SYS PHB PHB PIX PXB SYS SYS PHB 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

Hypervisor vendor:: KVM
ulimit soft: 102400