[Bug]: Speculative Decoding Issue with VLLM_ENABLE_V1_MULTIPROCESSING=0 #27287
Description
Your current environment
The output of python collect_env.py
Collecting environment information...
uv is set
==============================
System Info
==============================
OS : Ubuntu 24.04.2 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 : 2.8.0+cu128
Is debug build : False
CUDA used to build PyTorch : 12.8
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.3 (main, Jun 18 2025, 17:59:45) [GCC 13.3.0] (64-bit runtime)
Python platform : Linux-6.11.0-29-generic-x86_64-with-glibc2.39
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.8.93
CUDA_MODULE_LOADING set to : LAZY
GPU models and configuration : GPU 0: NVIDIA H100 80GB HBM3
Nvidia driver version : 570.158.01
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.10.2
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.10.2
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: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 26
On-line CPU(s) list: 0-25
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8480+
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 13
Socket(s): 1
Stepping: 8
BogoMIPS: 4000.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 832 KiB (26 instances)
L1i cache: 832 KiB (26 instances)
L2 cache: 52 MiB (13 instances)
L3 cache: 16 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-25
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: Unknown: No mitigations
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 SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; TSX disabled
==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.3.1
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.15.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-ml-py==13.580.82
[pip3] nvidia-nccl-cu12==2.27.3
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pynvml==13.0.1
[pip3] pyzmq==27.1.0
[pip3] torch==2.8.0
[pip3] torchaudio==2.8.0
[pip3] torchvision==0.23.0
[pip3] transformers==4.56.1
[pip3] triton==3.4.0
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.11.1.dev18+g650bf20f6 (git sha: 650bf20f6)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
�[4mGPU0 NIC0 CPU Affinity NUMA Affinity GPU NUMA ID�[0m
GPU0 X PHB 0-25 0 N/A
NIC0 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
==============================
Environment Variables
==============================
LD_LIBRARY_PATH=/usr/mpi/gcc/openmpi-4.1.7rc1/lib:/usr/mpi/gcc/openmpi-4.1.7rc1/lib64
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
Description of the Issue
The speculative decoding doesn't seem to work properly when setting VLLM_ENABLE_V1_MULTIPROCESSING=0
- Example commands with multi_proc disabled (spec doesn't work)
VLLM_ENABLE_V1_MULTIPROCESSING=0 python examples/offline_inference/spec_decode.py --method ngram
Output ==>
-------------------------------------------------
total_num_output_tokens: 247573
num_drafts: 0
num_draft_tokens: 0
num_accepted_tokens: 0
mean acceptance length: 1.00
--------------------------------------------------
acceptance at token 0: 0.00
acceptance at token 1: 0.00
- Example commands with multi_proc enabled (default) (spec work properly)
python examples/offline_inference/spec_decode.py --method ngram
Output ==>
--------------------------------------------------
total_num_output_tokens: 248291
num_drafts: 74097
num_draft_tokens: 147899
num_accepted_tokens: 141162
mean acceptance length: 2.91
--------------------------------------------------
acceptance at token 0: 0.96
acceptance at token 1: 0.94
Possible Reason
It appears that the post_step() function in EngineCore, which updates the draft_token_token_ids and returns them to the scheduler, is never invoked, resulting in proposed spec_tokens failing to be scheduled.
Potential Fix
diff --git a/vllm/v1/engine/core_client.py b/vllm/v1/engine/core_client.py
index a84b0e551..757c141fd 100644
--- a/vllm/v1/engine/core_client.py
+++ b/vllm/v1/engine/core_client.py
@@ -245,7 +245,8 @@ class InprocClient(EngineCoreClient):
self.engine_core = EngineCore(*args, **kwargs)
def get_output(self) -> EngineCoreOutputs:
- outputs, _ = self.engine_core.step_fn()
+ outputs, model_executed = self.engine_core.step_fn()
+ self.engine_core.post_step(model_executed)
return outputs and outputs.get(0) or EngineCoreOutputs()
Reference
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.