[Bug]: Fused MoE errors without safe serialization #30995
Description
Your current environment
The output of python collect_env.py
Collecting environment information...
uv is set
==============================
System Info
==============================
OS : Ubuntu 24.04.1 LTS (x86_64)
GCC version : (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version : Could not collect
CMake version : version 3.28.3
Libc version : glibc-2.39
==============================
PyTorch Info
==============================
PyTorch version : 2.9.0+cu128
Is debug build : False
CUDA used to build PyTorch : 12.8
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.12 (main, Dec 9 2025, 19:02:36) [Clang 21.1.4 ] (64-bit runtime)
Python platform : Linux-5.15.0-164-generic-x86_64-with-glibc2.39
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.8.93
CUDA_MODULE_LOADING set to :
GPU models and configuration :
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3
Nvidia driver version : 570.124.06
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.8.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.8.0
HIP runtime version : N/A
MIOpen runtime version : N/A
Is XNNPACK available : True
==============================
CPU Info
==============================
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 104
On-line CPU(s) list: 0-103
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8470
CPU family: 6
Model: 143
Thread(s) per core: 1
Core(s) per socket: 52
Socket(s): 2
Stepping: 8
BogoMIPS: 4000.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities ibpb_exit_to_user
L1d cache: 4.9 MiB (104 instances)
L1i cache: 3.3 MiB (104 instances)
L2 cache: 208 MiB (104 instances)
L3 cache: 210 MiB (2 instances)
NUMA node(s): 8
NUMA node0 CPU(s): 0-12
NUMA node1 CPU(s): 13-25
NUMA node2 CPU(s): 26-38
NUMA node3 CPU(s): 39-51
NUMA node4 CPU(s): 52-64
NUMA node5 CPU(s): 65-77
NUMA node6 CPU(s): 78-90
NUMA node7 CPU(s): 91-103
Vulnerability Gather data sampling: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Mitigation; IBPB before exit to userspace
==============================
Versions of relevant libraries
==============================
[pip3] No relevant packages
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.11.1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 NIC10 NIC11 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX PIX PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS 0-12 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS 26-38 2 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS 39-51 3 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS 13-25 1 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS SYS PIX PIX PIX SYS SYS SYS 52-64 4 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX SYS SYS 78-90 6 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX SYS 91-103 7 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX 65-77 5 N/A
NIC0 PIX SYS SYS SYS SYS SYS SYS SYS X PIX PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC1 PIX SYS SYS SYS SYS SYS SYS SYS PIX X PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC2 PIX SYS SYS SYS SYS SYS SYS SYS PIX PIX X SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC3 SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS SYS SYS
NIC4 SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS SYS
NIC5 SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS
NIC6 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS X PIX PIX SYS SYS SYS
NIC7 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX X PIX SYS SYS SYS
NIC8 SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX PIX X SYS SYS SYS
NIC9 SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS
NIC10 SYS SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X SYS
NIC11 SYS SYS SYS SYS SYS SYS SYS PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS 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
==============================
Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566
NCCL_VERSION=2.25.1-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=12.8.1
LD_LIBRARY_PATH=/usr/local/cuda/lib64
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
🐛 Describe the bug
VLLM MoE LoRA loading errors if the lora was saved without safe_serialization:
RuntimeError: Worker failed with error 'While loading /vast_storage/afterburner/afterburner-20251217-fsdp2-qwen30ba3b-grpo-seed-0/lora/step_0, expected target modules in ['experts.48.gate_proj', 'experts.68.down_proj', 'experts.65.gate_proj', 'experts.48.down_proj', 'experts.91.up_proj', 'experts.61.down_proj',
…
'experts.109.down_proj'] but received ['up_proj', 'down_proj', 'gate_proj']. Please verify that the loaded LoRA module is correct'
Script to reproduce, works if and only if SAFE_SERIALIZATION is set to True:
#!/usr/bin/env python3
"""
Minimal script to test Qwen3-30B-A3B with LoRA adapter:
1. Load model with HF + PEFT
2. Initialize and save LoRA adapter
3. Clear memory
4. Load model with VLLM
5. Load saved LoRA adapter
6. Generate example tokens
"""
import gc
import os
import torch
from peft import LoraConfig, get_peft_model
from transformers import AutoModelForCausalLM, AutoTokenizer
from vllm import LLM, SamplingParams
from vllm.lora.request import LoRARequest
# Configuration
MODEL_NAME = "Qwen/Qwen3-30B-A3B"
LORA_SAVE_PATH = LORA_LOAD_PATH = "/tmp/qwen_test_lora"
LORA_RANK = 8
LORA_ALPHA = 16
SAFE_SERIALIZATION = False
print(f"Loading tokenizer for {MODEL_NAME}...")
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
print(f"Tokenizer loaded: {MODEL_NAME}")
print("=" * 80)
print("Step 1: Load model with HuggingFace")
print("=" * 80)
model = AutoModelForCausalLM.from_pretrained(
MODEL_NAME,
torch_dtype=torch.bfloat16,
)
print(f"Model loaded: {MODEL_NAME}")
print("\n" + "=" * 80)
print("Step 2: Initialize LoRA adapter")
print("=" * 80)
lora_config = LoraConfig(
r=LORA_RANK,
lora_alpha=LORA_ALPHA,
target_modules="all-linear",
lora_dropout=0,
bias="none",
task_type="CAUSAL_LM",
)
peft_model = get_peft_model(model, lora_config)
print(f"LoRA adapter initialized with rank={LORA_RANK}, alpha={LORA_ALPHA}")
peft_model.print_trainable_parameters()
print("\n" + "=" * 80)
print("Step 3: Save LoRA adapter to disk")
print("=" * 80)
os.makedirs(LORA_SAVE_PATH, exist_ok=True)
peft_model.save_pretrained(LORA_SAVE_PATH, safe_serialization=SAFE_SERIALIZATION)
print(f"LoRA adapter saved to: {LORA_SAVE_PATH}")
print("\n" + "=" * 80)
print("Step 4: Clear memory")
print("=" * 80)
del peft_model
del model
gc.collect()
torch.cuda.empty_cache()
print("Memory cleared")
print("\n" + "=" * 80)
print("Step 5: Load model with VLLM")
print("=" * 80)
llm = LLM(
model=MODEL_NAME,
enable_lora=True,
max_lora_rank=64,
dtype="bfloat16",
enforce_eager=True,
max_model_len=128,
gpu_memory_utilization=0.95,
)
print(f"VLLM model loaded: {MODEL_NAME}")
print("\n" + "=" * 80)
print("Step 6: Generate tokens with LoRA adapter")
print("=" * 80)
# Create sampling parameters
sampling_params = SamplingParams(
temperature=0.7,
top_p=0.9,
max_tokens=50,
)
# Test prompts with chat template
messages_list = [
[{"role": "user", "content": "What is the capital of France?"}],
[{"role": "user", "content": "Explain quantum computing in one sentence:"}],
]
# Apply chat template
prompts = [tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) for messages in messages_list]
# Generate with LoRA adapter
lora_request = LoRARequest("test_lora", 1, LORA_LOAD_PATH)
print(f"\nGenerating with LoRA adapter from: {LORA_LOAD_PATH}")
print("-" * 80)
outputs = llm.generate(prompts, sampling_params, lora_request=lora_request)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt}")
print(f"Generated: {generated_text}")
print("-" * 80)
print("\n" + "=" * 80)
print("✓ Script completed successfully!")
print("=" * 80)
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.