[Bug]: calculate_kv_scales leads to dynamo compilation issue; enforce_eager=True leads to another issue #21640
Description
Your current environment
The output of python collect_env.py
# For security purposes, please feel free to check the contents of collect_env.py before running it.
python collect_env.py
--2025-07-26 00:45:07-- https://raw.githubusercontent.com/vllm-project/vllm/main/vllm/collect_env.py
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 28526 (28K) [text/plain]
Saving to: ‘collect_env.py’
collect_env.py 100%[================================================================================================================================================================================================================================>] 27.86K --.-KB/s in 0.006s
2025-07-26 00:45:08 (4.52 MB/s) - ‘collect_env.py’ saved [28526/28526]
Collecting environment information...
==============================
System Info
==============================
OS : Ubuntu 22.04.5 LTS (x86_64)
GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version : Could not collect
CMake version : version 3.22.1
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.7.1+cu126
Is debug build : False
CUDA used to build PyTorch : 12.6
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.10.18 (main, Jun 5 2025, 13:14:17) [GCC 11.2.0] (64-bit runtime)
Python platform : Linux-6.8.0-60-generic-x86_64-with-glibc2.35
==============================
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
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 : 570.148.08
cuDNN version : Could not collect
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): 208
On-line CPU(s) list: 0-207
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: 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 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: 6.5 MiB (208 instances)
L1i cache: 6.5 MiB (208 instances)
L2 cache: 416 MiB (104 instances)
L3 cache: 32 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-103
NUMA node1 CPU(s): 104-207
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] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-cufile-cu12==1.11.1.6
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] pyzmq==27.0.0
[pip3] torch==2.7.1
[pip3] torchaudio==2.7.1
[pip3] torchvision==0.22.1
[pip3] transformers==4.54.0
[pip3] triton==3.3.1
[conda] numpy 2.2.6 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.6.4.1 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.6.80 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.6.77 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.6.77 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.5.1.17 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.3.0.4 pypi_0 pypi
[conda] nvidia-cufile-cu12 1.11.1.6 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.7.77 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.7.1.2 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.5.4.2 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.6.3 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.26.2 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.6.85 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.6.77 pypi_0 pypi
[conda] pyzmq 27.0.0 pypi_0 pypi
[conda] torch 2.7.1 pypi_0 pypi
[conda] torchaudio 2.7.1 pypi_0 pypi
[conda] torchvision 0.22.1 pypi_0 pypi
[conda] transformers 4.54.0 pypi_0 pypi
[conda] triton 3.3.1 pypi_0 pypi
==============================
vLLM Info
==============================
ROCM Version : Could not collect
Neuron SDK Version : N/A
vLLM Version : 0.10.0
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 SYS 0-103 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 SYS 0-103 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 SYS 0-103 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 SYS 0-103 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS 104-207 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS 104-207 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS 104-207 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS 104-207 1 N/A
NIC0 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
==============================
Environment Variables
==============================
LD_LIBRARY_PATH=/usr/mpi/gcc/openmpi-4.1.7rc1/lib:/usr/mpi/gcc/openmpi-4.1.7rc1/lib64
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
I am on v0.10.0. The argument calculate_kv_scales=True does not seem to work.
If enforce_eager=False
With code:
import vllm
def main():
engine = vllm.LLM(
model="/home/ubuntu/models/Qwen3-8B",
tensor_parallel_size=2,
kv_cache_dtype="fp8_e4m3",
calculate_kv_scales=True,
)
output = engine.generate("Hello, world!")
print(output)
if __name__ == "__main__":
main()I run into
RuntimeError: Worker failed with error 'Data-dependent branching
Explanation: Detected data-dependent branching (e.g. `if my_tensor.sum() > 0:`). Dynamo does not support tracing dynamic control flow.
Hint: This graph break is fundamental - it is unlikely that Dynamo will ever be able to trace through your code. Consider finding a workaround.
Hint: Use `torch.cond` to express dynamic control flow.
Developer debug context: attempted to jump with GetAttrVariable(ConstantVariable(NoneType: None), enable_kv_scales_calculation)
from user code:
File "/home/ubuntu/miniconda3/envs/vllm-new/lib/python3.10/site-packages/vllm/model_executor/models/qwen2.py", line 354, in forward
hidden_states, residual = layer(
File "/home/ubuntu/miniconda3/envs/vllm-new/lib/python3.10/site-packages/vllm/model_executor/models/qwen3.py", line 214, in forward
hidden_states = self.self_attn(
File "/home/ubuntu/miniconda3/envs/vllm-new/lib/python3.10/site-packages/vllm/model_executor/models/qwen3.py", line 145, in forward
attn_output = self.attn(q, k, v)
File "/home/ubuntu/miniconda3/envs/vllm-new/lib/python3.10/site-packages/vllm/attention/layer.py", line 239, in forward
if attn_metadata.enable_kv_scales_calculation:Full log here https://gist.github.com/CharlieFRuan/7bfa12f029ddeef496996e5864979530
If enforce_eager=True
With code:
import vllm
def main():
engine = vllm.LLM(
model="/home/ubuntu/models/Qwen3-8B",
tensor_parallel_size=2,
kv_cache_dtype="fp8_e4m3",
calculate_kv_scales=True,
enforce_eager=True,
)
output = engine.generate("Hello, world!")
print(output)
if __name__ == "__main__":
main()I run into
(VllmWorker rank=1 pid=87573) ERROR 07-26 00:49:21 [multiproc_executor.py:546] File "/home/ubuntu/miniconda3/envs/vllm-new/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
(VllmWorker rank=1 pid=87573) ERROR 07-26 00:49:21 [multiproc_executor.py:546] return forward_call(*args, **kwargs)
(VllmWorker rank=1 pid=87573) ERROR 07-26 00:49:21 [multiproc_executor.py:546] File "/home/ubuntu/miniconda3/envs/vllm-new/lib/python3.10/site-packages/vllm/attention/layer.py", line 239, in forward
(VllmWorker rank=1 pid=87573) ERROR 07-26 00:49:21 [multiproc_executor.py:546] if attn_metadata.enable_kv_scales_calculation:
(VllmWorker rank=1 pid=87573) ERROR 07-26 00:49:21 [multiproc_executor.py:546] AttributeError: 'NoneType' object has no attribute 'enable_kv_scales_calculation'Full log here: https://gist.github.com/CharlieFRuan/6bd380cb135c35aa0a70b80cf9e6eebd
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.