[Bug]: Can not run quantized models after #20694 #20832
Description
Your current environment
The output of python collect_env.py
Collecting environment information...
==============================
System Info
==============================
OS : Ubuntu 20.04.6 LTS (x86_64)
GCC version : (Ubuntu 11.4.0-2ubuntu1~20.04) 11.4.0
Clang version : 10.0.0-4ubuntu1
CMake version : version 4.0.3
Libc version : glibc-2.31
==============================
PyTorch Info
==============================
PyTorch version : 2.7.0+cu128
Is debug build : False
CUDA used to build PyTorch : 12.8
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.9 (main, Feb 12 2025, 14:50:50) [Clang 19.1.6 ] (64-bit runtime)
Python platform : Linux-5.13.0-30-generic-x86_64-with-glibc2.31
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.1.66
CUDA_MODULE_LOADING set to : LAZY
GPU models and configuration :
GPU 0: NVIDIA GeForce RTX 3090
GPU 1: NVIDIA GeForce RTX 3090
GPU 2: NVIDIA GeForce RTX 3090
GPU 3: NVIDIA GeForce RTX 3090
GPU 4: NVIDIA GeForce RTX 3090
GPU 5: NVIDIA GeForce RTX 3090
GPU 6: NVIDIA GeForce RTX 3090
GPU 7: NVIDIA GeForce RTX 3090
Nvidia driver version : 530.30.02
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.6.0
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
Byte Order: Little Endian
Address sizes: 46 bits physical, 48 bits virtual
CPU(s): 56
On-line CPU(s) list: 0-55
Thread(s) per core: 2
Core(s) per socket: 14
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 79
Model name: Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz
Stepping: 1
CPU MHz: 1200.000
CPU max MHz: 3300.0000
CPU min MHz: 1200.0000
BogoMIPS: 4799.70
Virtualization: VT-x
L1d cache: 896 KiB
L1i cache: 896 KiB
L2 cache: 7 MiB
L3 cache: 70 MiB
NUMA node0 CPU(s): 0-13,28-41
NUMA node1 CPU(s): 14-27,42-55
Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled
Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Meltdown: Mitigation; PTI
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; Full generic retpoline, IBPB conditional, IBRS_FW, STIBP conditional, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable
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 arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor 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 cdp_l3 invpcid_single pti intel_ppin ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap intel_pt xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts md_clear flush_l1d
==============================
Versions of relevant libraries
==============================
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.8.3.14
[pip3] nvidia-cuda-cupti-cu12==12.8.57
[pip3] nvidia-cuda-nvrtc-cu12==12.8.61
[pip3] nvidia-cuda-runtime-cu12==12.8.57
[pip3] nvidia-cudnn-cu12==9.7.1.26
[pip3] nvidia-cufft-cu12==11.3.3.41
[pip3] nvidia-cufile-cu12==1.13.0.11
[pip3] nvidia-curand-cu12==10.3.9.55
[pip3] nvidia-cusolver-cu12==11.7.2.55
[pip3] nvidia-cusparse-cu12==12.5.7.53
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-ml-py==12.575.51
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.8.61
[pip3] nvidia-nvshmem-cu12==3.3.9
[pip3] nvidia-nvtx-cu12==12.8.55
[pip3] onnx==1.18.0
[pip3] onnx-ir==0.1.4
[pip3] onnxruntime-gpu==1.22.0
[pip3] onnxscript==0.3.1
[pip3] open_clip_torch==2.32.0
[pip3] pynvml==12.0.0
[pip3] pyzmq==27.0.0
[pip3] sentence-transformers==5.0.0
[pip3] torch==2.7.0+cu128
[pip3] torchao==0.11.0
[pip3] torchaudio==2.7.0+cu128
[pip3] torchdata==0.11.0
[pip3] torchtitan==0.1.0
[pip3] torchvision==0.22.0+cu128
[pip3] transformers==4.53.2
[pip3] triton==3.3.0
[conda] mkl 2024.2.2 ha957f24_16 conda-forge
[conda] mkl-devel 2024.2.2 ha770c72_16 conda-forge
[conda] mkl-include 2024.2.2 ha957f24_16 conda-forge
[conda] mkl-service 2.4.2 py310h22455d7_0 conda-forge
[conda] mkl_fft 1.3.11 py310h5bcb89a_0 conda-forge
[conda] mkl_random 1.2.8 py310hcacb51e_1 conda-forge
[conda] numpy 2.1.3 py310heeff2f4_0
[conda] numpy-base 2.1.3 py310h8a23956_0
[conda] nvidia-ml-py 12.535.108 pypi_0 pypi
[conda] transformers 4.53.1 pypi_0 pypi
==============================
vLLM Info
==============================
ROCM Version : Could not collect
Neuron SDK Version : N/A
vLLM Version : 0.9.2rc2.dev176+g9907fc449 (git sha: 9907fc449)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity
GPU0 X PIX PHB PHB SYS SYS SYS SYS 0-13,28-41 0
GPU1 PIX X PHB PHB SYS SYS SYS SYS 0-13,28-41 0
GPU2 PHB PHB X PIX SYS SYS SYS SYS 0-13,28-41 0
GPU3 PHB PHB PIX X SYS SYS SYS SYS 0-13,28-41 0
GPU4 SYS SYS SYS SYS X PIX PHB PHB 14-27,42-55 1
GPU5 SYS SYS SYS SYS PIX X PHB PHB 14-27,42-55 1
GPU6 SYS SYS SYS SYS PHB PHB X PIX 14-27,42-55 1
GPU7 SYS SYS SYS SYS PHB PHB PIX X 14-27,42-55 1
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
==============================
Environment Variables
==============================
LD_LIBRARY_PATH=/usr/local/cuda-12.1/lib64:/usr/local/cuda-12.1/lib64
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
Cannot run quantized models(Qwen3-32B-AWQ) on my 3090 after pr #20694 @mgoin
Process EngineCore_0:
Traceback (most recent call last):
File "/home/mosh/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/home/mosh/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 590, in run_engine_core
raise e
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 577, in run_engine_core
engine_core = EngineCoreProc(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 404, in __init__
super().__init__(vllm_config, executor_class, log_stats,
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 75, in __init__
self.model_executor = executor_class(vllm_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 53, in __init__
self._init_executor()
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 48, in _init_executor
self.collective_rpc("load_model")
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 57, in collective_rpc
answer = run_method(self.driver_worker, method, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/utils/__init__.py", line 2943, in run_method
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/worker/gpu_worker.py", line 194, in load_model
self.model_runner.load_model()
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/worker/gpu_model_runner.py", line 1738, in load_model
self.model = model_loader.load_model(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/model_executor/model_loader/base_loader.py", line 42, in load_model
process_weights_after_loading(model, model_config, target_device)
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/model_executor/model_loader/utils.py", line 113, in process_weights_after_loading
quant_method.process_weights_after_loading(module)
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/awq_marlin.py", line 283, in process_weights_after_loading
marlin_scales = marlin_permute_scales(
^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/marlin_utils.py", line 256, in marlin_permute_scales
s = s.reshape((-1, len(scale_perm)))[:, scale_perm]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^
RuntimeError: CUDA error: invalid resource handle
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
[rank0]:[W712 01:41:12.596494424 ProcessGroupNCCL.cpp:1476] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
Traceback (most recent call last):
File "/data/lijinghui/uv_projects/LLM/chat_xiaoai.py", line 1387, in <module>
engine = initialize_engine()
^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/LLM/chat_xiaoai.py", line 942, in initialize_engine
return AsyncLLMEngine.from_engine_args(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 189, in from_engine_args
return cls(
^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/async_llm.py", line 124, in __init__
self.engine_core = EngineCoreClient.make_async_mp_client(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 96, in make_async_mp_client
return AsyncMPClient(*client_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 666, in __init__
super().__init__(
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 403, in __init__
with launch_core_engines(vllm_config, executor_class,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mosh/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 144, in __exit__
next(self.gen)
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 444, in launch_core_engines
wait_for_engine_startup(
File "/data/lijinghui/uv_projects/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 494, in wait_for_engine_startup
raise RuntimeError("Engine core initialization failed. "
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}
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.