[Bug]: Loading mistralai/Mixtral-8x22B-Instruct-v0.1 raises TypeError: a bytes-like object is required, not 'str'

[brnrc]

Your current environment

The output of `python collect_env.py`

Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Debian GNU/Linux 11 (bullseye) (x86_64)
GCC version: (Debian 10.2.1-6) 10.2.1 20210110
Clang version: Could not collect
CMake version: version 3.30.5
Libc version: glibc-2.31

Python version: 3.10.15 | packaged by conda-forge | (main, Sep 20 2024, 16:37:05) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-5.10.0-32-cloud-amd64-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA A100-SXM4-80GB
GPU 1: NVIDIA A100-SXM4-80GB
GPU 2: NVIDIA A100-SXM4-80GB
GPU 3: NVIDIA A100-SXM4-80GB
GPU 4: NVIDIA A100-SXM4-80GB
GPU 5: NVIDIA A100-SXM4-80GB
GPU 6: NVIDIA A100-SXM4-80GB
GPU 7: NVIDIA A100-SXM4-80GB

Nvidia driver version: 550.90.07
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
Byte Order:                           Little Endian
Address sizes:                        46 bits physical, 48 bits virtual
CPU(s):                               96
On-line CPU(s) list:                  0-95
Thread(s) per core:                   2
Core(s) per socket:                   24
Socket(s):                            2
NUMA node(s):                         2
Vendor ID:                            GenuineIntel
CPU family:                           6
Model:                                85
Model name:                           Intel(R) Xeon(R) CPU @ 2.20GHz
Stepping:                             7
CPU MHz:                              2200.198
BogoMIPS:                             4400.39
Hypervisor vendor:                    KVM
Virtualization type:                  full
L1d cache:                            1.5 MiB
L1i cache:                            1.5 MiB
L2 cache:                             48 MiB
L3 cache:                             77 MiB
NUMA node0 CPU(s):                    0-23,48-71
NUMA node1 CPU(s):                    24-47,72-95
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:        Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Mitigation; Enhanced IBRS
Vulnerability Spec rstack overflow:   Not affected
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; Enhanced / Automatic IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
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 rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat avx512_vnni md_clear arch_capabilities

Versions of relevant libraries:
[pip3] numpy==1.25.2
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==11.495.46
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.6.77
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.46.0
[pip3] triton==3.0.0
[conda] numpy                     1.25.2                   pypi_0    pypi
[conda] nvidia-cublas-cu12        12.1.3.1                 pypi_0    pypi
[conda] nvidia-cuda-cupti-cu12    12.1.105                 pypi_0    pypi
[conda] nvidia-cuda-nvrtc-cu12    12.1.105                 pypi_0    pypi
[conda] nvidia-cuda-runtime-cu12  12.1.105                 pypi_0    pypi
[conda] nvidia-cudnn-cu12         9.1.0.70                 pypi_0    pypi
[conda] nvidia-cufft-cu12         11.0.2.54                pypi_0    pypi
[conda] nvidia-curand-cu12        10.3.2.106               pypi_0    pypi
[conda] nvidia-cusolver-cu12      11.4.5.107               pypi_0    pypi
[conda] nvidia-cusparse-cu12      12.1.0.106               pypi_0    pypi
[conda] nvidia-ml-py              11.495.46                pypi_0    pypi
[conda] nvidia-nccl-cu12          2.20.5                   pypi_0    pypi
[conda] nvidia-nvjitlink-cu12     12.6.77                  pypi_0    pypi
[conda] nvidia-nvtx-cu12          12.1.105                 pypi_0    pypi
[conda] pyzmq                     26.2.0                   pypi_0    pypi
[conda] torch                     2.4.0                    pypi_0    pypi
[conda] torchvision               0.19.0                   pypi_0    pypi
[conda] transformers              4.46.0                   pypi_0    pypi
[conda] triton                    3.0.0                    pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.post1
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   GPU NUMA ID
GPU0     X      NV12    NV12    NV12    NV12    NV12    NV12    NV12    0-23,48-71      0               N/A
GPU1    NV12     X      NV12    NV12    NV12    NV12    NV12    NV12    0-23,48-71      0               N/A
GPU2    NV12    NV12     X      NV12    NV12    NV12    NV12    NV12    0-23,48-71      0               N/A
GPU3    NV12    NV12    NV12     X      NV12    NV12    NV12    NV12    0-23,48-71      0               N/A
GPU4    NV12    NV12    NV12    NV12     X      NV12    NV12    NV12    24-47,72-95     1               N/A
GPU5    NV12    NV12    NV12    NV12    NV12     X      NV12    NV12    24-47,72-95     1               N/A
GPU6    NV12    NV12    NV12    NV12    NV12    NV12     X      NV12    24-47,72-95     1               N/A
GPU7    NV12    NV12    NV12    NV12    NV12    NV12    NV12     X      24-47,72-95     1               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

🐛 Describe the bug

When trying to serve mistralai/Mixtral-8x22B-Instruct-v0.1 in a single-node with 8 GPUs I get the error below:

VLLM_LOGGING_LEVEL=DEBUG python -m vllm.entrypoints.openai.api_server  \
  --model mistralai/Mixtral-8x22B-Instruct-v0.1   \
  --tensor-parallel-size 8   \
  --tokenizer-mode="mistral"

...

INFO 10-29 22:43:58 multiproc_worker_utils.py:120] Killing local vLLM worker processes
DEBUG 10-29 22:43:58 client.py:170] Waiting for output from MQLLMEngine.
Process SpawnProcess-1:
Traceback (most recent call last):
  File "/opt/conda/lib/python3.10/site-packages/vllm/worker/model_runner_base.py", line 116, in _wrapper
    return func(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 1658, in execute_model
    hidden_or_intermediate_states = model_executable(
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/models/mixtral.py", line 380, in forward
    hidden_states = self.model(input_ids, positions, kv_caches,
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/models/mixtral.py", line 300, in forward
    hidden_states, residual = layer(positions, hidden_states,
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/models/mixtral.py", line 244, in forward
    hidden_states = self.block_sparse_moe(hidden_states)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/models/mixtral.py", line 101, in forward
    final_hidden_states = self.experts(hidden_states, router_logits)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/layers/fused_moe/layer.py", line 474, in forward
    final_hidden_states = self.quant_method.apply(
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/layers/quantization/fp8.py", line 495, in apply
    return fused_experts(x,
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 510, in fused_experts
    config = get_config_func(M)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 369, in try_get_optimal_moe_config
    configs = get_moe_configs(E, N, dtype)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 310, in get_moe_configs
    json_file_name = get_config_file_name(E, N, dtype)
  File "/opt/conda/lib/python3.10/site-packages/vllm/model_executor/layers/fused_moe/fused_moe.py", line 291, in get_config_file_name
    device_name = current_platform.get_device_name().replace(" ", "_")
TypeError: a bytes-like object is required, not 'str'

You can reproduce the error with the cli above (and a similar environment) or with the snippet below:

from vllm.platforms import current_platform
print(current_platform)
current_platform.get_device_name().replace(" ", "_")

$ python
Python 3.10.15 | packaged by conda-forge | (main, Sep 20 2024, 16:37:05) [GCC 13.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from vllm.platforms import current_platform
>>> print(current_platform)
<vllm.platforms.cuda.CudaPlatform object at 0x7fa6bca82b30>
>>> name = current_platform.get_device_name()
>>> name
b'NVIDIA A100-SXM4-80GB'
>>> name.replace(" ", "_")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: a bytes-like object is required, not 'str'

[brnrc]

I managed to fix this by explicitly casting the device name to str, since current_platform.get_device_name() is returning bytes instead of str. After applying the patch I can load the model without problems.

diff --git a/vllm/model_executor/layers/fused_moe/fused_moe.py b/vllm/model_executor/layers/fused_moe/fused_moe.py
index 1cf5c225..b43bb39a 100644
--- a/vllm/model_executor/layers/fused_moe/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py
@@ -288,7 +288,7 @@ def invoke_fused_moe_kernel(A: torch.Tensor, B: torch.Tensor, C: torch.Tensor,
 
 
 def get_config_file_name(E: int, N: int, dtype: Optional[str]) -> str:
-    device_name = current_platform.get_device_name().replace(" ", "_")
+    device_name = str(current_platform.get_device_name()).replace(" ", "_")
     dtype_selector = "" if not dtype else f",dtype={dtype}"
     return f"E={E},N={N},device_name={device_name}{dtype_selector}.json"

[jeejeelee]

It look likes your nvidia-ml-py is old , you can try updating it :

pip install nvidia-ml-py==12.560.30

[brnrc]

It look likes your nvidia-ml-py is old , you can try updating it :

pip install nvidia-ml-py==12.560.30

@jeejeelee Thank you for the quick reply. What do you think of setting a minimum version for nvidia-ml-py? Seems like the version pinning was dropped after moving away from pynvml (e4bf860).

- nvidia-ml-py # for pynvml package
+ nvidia-ml-py >= 12.560.30 # for pynvml package 

[jeejeelee]

IMHO, we should add a minimum version, cc @youkaichao

[youkaichao]

sounds good, we can specify nvidia-ml-py >= 12.560.30