[Bug][V1] Structured output FSM failures should be handled gracefully without aborting requests

[atbe]

Your current environment

INFO 05-27 16:20:01 [__init__.py:239] Automatically detected platform cuda.
Collecting environment information...
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 4.0.0
Libc version: glibc-2.35

Python version: 3.12.10 (main, Apr  9 2025, 08:55:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.8.0-59-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA H200
Nvidia driver version: 550.144.03
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
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):                               192
On-line CPU(s) list:                  0-191
Vendor ID:                            GenuineIntel
Model name:                           INTEL(R) XEON(R) PLATINUM 8568Y+
CPU family:                           6
Model:                                207
Thread(s) per core:                   2
Core(s) per socket:                   48
Socket(s):                            2
Stepping:                             2
CPU max MHz:                          4000.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4600.00
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 ds_cpl vmx 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 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi 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 ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            4.5 MiB (96 instances)
L1i cache:                            3 MiB (96 instances)
L2 cache:                             192 MiB (96 instances)
L3 cache:                             600 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-47,96-143
NUMA node1 CPU(s):                    48-95,144-191
Vulnerability Gather data sampling:   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
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] numpy==2.2.5
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-ml-py==12.575.51
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pynvml==12.0.0
[pip3] pyzmq==26.4.0
[pip3] torch==2.6.0
[pip3] torchao==0.11.0
[pip3] torchaudio==2.6.0
[pip3] torchvision==0.21.0
[pip3] transformers==4.51.1
[pip3] triton==3.2.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.8.5
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
        GPU0    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    NIC8    NIC9    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    NODE    PIX     NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-47,96-143     0               N/A
NIC0    NODE     X      NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS
NIC1    NODE    NODE     X      NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS
NIC2    PIX     NODE    NODE     X      NODE    SYS     SYS     SYS     SYS     SYS     SYS
NIC3    NODE    NODE    NODE    NODE     X      SYS     SYS     SYS     SYS     SYS     SYS
NIC4    SYS     SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    NODE    NODE
NIC5    SYS     SYS     SYS     SYS     SYS     NODE     X      NODE    NODE    NODE    NODE
NIC6    SYS     SYS     SYS     SYS     SYS     NODE    NODE     X      NODE    NODE    NODE
NIC7    SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE     X      NODE    NODE
NIC8    SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE     X      PIX
NIC9    SYS     SYS     SYS     SYS     SYS     NODE    NODE    NODE    NODE    PIX      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

NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536
NCCL_VERSION=2.20.5-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_PRODUCT_NAME=CUDA
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.4.0
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY

Current Behavior

When the structured output FSM (Finite State Machine) fails to advance in the xgrammar backend, the current implementation aborts the entire request. This happens when accept_tokens() returns False, indicating the generated tokens don't conform to the specified grammar/schema.

if not request.structured_output_request.grammar.accept_tokens(req_id, new_token_ids):
    # Grammar FSM failed to advance - mark request as finished with error
    logger.error(
        "Structured output FSM failed to advance for request %s. "
        "Terminating request.", req_id)
    request.status = RequestStatus.FINISHED_ABORTED
    stopped = True
    self._free_request(request)

Expected Behavior

The system should handle FSM failures more gracefully, potentially by:

• Retrying with alternative tokens that satisfy the grammar
• Backtracking to a valid state and regenerating
• Providing more detailed error information to help debug grammar/schema issues
• Allowing configurable behavior (abort vs. retry)

Impact

• Users experience aborted requests when structured output constraints cannot be satisfied
• No opportunity for recovery or alternative generation strategies
• Limited debugging information about why the FSM failed

Reproduction Steps

1. Use structured output with a restrictive JSON schema or grammar
2. Generate content that would produce tokens violating the schema
3. Request aborts with FINISHED_ABORTED status

Environment

• vLLM version: v1 engine
• Backend: xgrammar
• Feature: Structured outputs (JSON schema, regex, grammar)

Related Code

• vllm/v1/core/sched/scheduler.py: Lines 782-790
• vllm/v1/structured_output/backend_xgrammar.py: accept_tokens() method

Proposed Solutions

1. Implement token rejection and resampling when FSM validation fails
2. Add backtracking capabilities to recover from invalid states
3. Provide detailed error context about which grammar rule was violated
4. Make abort-on-failure behavior configurable
5. Consider implementing constrained beam search for structured outputs

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.

[ekagra-ranjan]

1. Use structured output with a restrictive JSON schema or grammar

what is the JSON grammar used here?

[github-actions]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!