[Bug]: AssertionError on loading unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit

[thesillystudent]

Your current environment

The output of `python collect_env.py`

INFO 02-03 07:11:32 __init__.py:183] Automatically detected platform cuda.
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

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 3.31.1
Libc version: glibc-2.35

Python version: 3.12.0 (main, Dec 26 2024, 13:25:06) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.8.0-1020-aws-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 A10G
Nvidia driver version: 550.127.05
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:                        48 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               8
On-line CPU(s) list:                  0-7
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 7R32
CPU family:                           23
Model:                                49
Thread(s) per core:                   2
Core(s) per socket:                   4
Socket(s):                            1
Stepping:                             0
BogoMIPS:                             5600.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save rdpid
Hypervisor vendor:                    KVM
Virtualization type:                  full
L1d cache:                            128 KiB (4 instances)
L1i cache:                            128 KiB (4 instances)
L2 cache:                             2 MiB (4 instances)
L3 cache:                             16 MiB (1 instance)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-7
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:               Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow:   Vulnerable: Safe RET, no microcode
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; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] numpy==1.26.4
[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-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torchaudio==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.48.2
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.7.1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      0-7     0               N/A

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

LD_LIBRARY_PATH=/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/cv2/../../lib64:/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/aws-ofi-nccl/lib:/usr/local/cuda-12.4/lib:/usr/local/cuda-12.4/lib64:/usr/local/cuda-12.4:/usr/local/cuda-12.4/targets/x86_64-linux/lib/:/usr/local/cuda-12.4/extras/CUPTI/lib64:/usr/local/lib:/usr/lib:/opt/amazon/efa/lib:/opt/amazon/openmpi/lib:/opt/aws-ofi-nccl/lib:/usr/local/cuda-12.4/lib:/usr/local/cuda-12.4/lib64:/usr/local/cuda-12.4:/usr/local/cuda-12.4/targets/x86_64-linux/lib/:/usr/local/cuda-12.4/extras/CUPTI/lib64:/usr/local/lib:/usr/lib
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY

Model Input Dumps

No response

🐛 Describe the bug

Assertion error on loading mistral small 2501 with unsloth weights

python3 -m vllm.entrypoints.openai.api_server --model unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit --tool-call-parser mistral --enable-auto-tool-choice --max-model-len 8192 --gpu-memory-utilization 0.98 --download-dir ./models_cache --host 0.0.0.0 --port 8000 --quantization bitsandbytes --load-format bitsandbytes

Error trace -

File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 378, in run_mp_engine
    engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 121, in from_engine_args
    return cls(ipc_path=ipc_path,
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 73, in __init__
    self.engine = LLMEngine(*args, **kwargs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 271, in __init__
    self.model_executor = executor_class(vllm_config=vllm_config, )
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 49, in __init__
    self._init_executor()
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 40, in _init_executor
    self.collective_rpc("load_model")
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/executor/uniproc_executor.py", line 49, in collective_rpc
    answer = run_method(self.driver_worker, method, args, kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/utils.py", line 2208, in run_method
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/worker/worker.py", line 182, in load_model
    self.model_runner.load_model()
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/worker/model_runner.py", line 1113, in load_model
    self.model = get_model(vllm_config=self.vllm_config)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/model_loader/__init__.py", line 12, in get_model
    return loader.load_model(vllm_config=vllm_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/model_loader/loader.py", line 1201, in load_model
    self._load_weights(model_config, model)
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/model_loader/loader.py", line 1111, in _load_weights
    loaded_weights = model.load_weights(qweight_iterator)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/models/llama.py", line 565, in load_weights
    return loader.load_weights(
           ^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 233, in load_weights
    autoloaded_weights = set(self._load_module("", self.module, weights))
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 194, in _load_module
    yield from self._load_module(prefix,
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/models/utils.py", line 171, in _load_module
    loaded_params = module_load_weights(weights)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/models/llama.py", line 438, in load_weights
    weight_loader(param, loaded_weight)
  File "/home/ubuntu/.pyenv/versions/3.12.0/lib/python3.12/site-packages/vllm/model_executor/layers/linear.py", line 1113, in weight_loader
    assert param_data.shape == loaded_weight.shape

I printed param_data.shape - torch.Size([83886080, 1]) and loaded_weight.shape - torch.Size([5120, 32768])

Before submitting a new issue...

• [x] 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.