Cannot run on aarch64 Linux
Author: SuperCowProductsCreated Jul 5, 2026Updated Jul 5, 2026
System Info / 系統信息
Host OS: Asahi ALARM Hardware: M2 Macbook Air (16GB)
(.venv) root@80a09d6d82c7:/# uv --version
uv 0.11.26 (aarch64-unknown-linux-gnu)
(.venv) root@80a09d6d82c7:/# python --version
Python 3.12.13
(.venv) root@80a09d6d82c7:/# uv pip list
Package Version
---------------------------------------- -------------
accelerate 1.14.0
aiohappyeyeballs 2.7.1
aiohttp 3.14.1
aiosignal 1.4.0
annotated-doc 0.0.4
annotated-types 0.7.0
anthropic 0.116.0
anyio 4.14.1
apache-tvm-ffi 0.1.12
astor 0.8.1
attrs 26.1.0
blake3 1.0.9
cachetools 7.1.4
cbor2 6.1.3
certifi 2026.6.17
cffi 2.0.0
charset-normalizer 3.4.7
click 8.4.2
cloudpickle 3.1.2
compressed-tensors 0.17.0
cryptography 49.0.0
depyf 0.20.0
detect-installer 0.1.0
dill 0.4.1
diskcache 5.6.3
distro 1.9.0
dnspython 2.8.0
docstring-parser 0.18.0
einops 0.8.2
email-validator 2.3.0
fastapi 0.136.3
fastapi-cli 0.0.28
fastapi-cloud-cli 0.22.1
fastar 0.11.0
filelock 3.29.5
frozenlist 1.8.0
fsspec 2026.6.0
glmocr 0.1.5
googleapis-common-protos 1.75.0
grpcio 1.81.1
h11 0.16.0
hf-xet 1.5.1
httpcore 1.0.9
httptools 0.8.0
httpx 0.28.1
httpx-sse 0.4.3
huggingface-hub 1.22.0
idna 3.18
ijson 3.5.0
interegular 0.3.3
jinja2 3.1.6
jiter 0.16.0
jmespath 1.1.0
jsonschema 4.26.0
jsonschema-specifications 2025.9.1
lark 1.2.2
llguidance 1.7.6
llvmlite 0.47.0
lm-format-enforcer 0.11.3
loguru 0.7.3
markdown-it-py 4.2.0
markupsafe 3.0.3
mcp 1.28.1
mdurl 0.1.2
mistral-common 1.11.5
model-hosting-container-standards 0.1.16
mpmath 1.3.0
msgspec 0.21.1
multidict 6.7.1
networkx 3.6.1
ninja 1.13.0
numba 0.65.0
numpy 2.3.5
openai 2.44.0
openai-harmony 0.0.8
opencv-python-headless 5.0.0.93
opentelemetry-api 1.43.0
opentelemetry-exporter-otlp 1.43.0
opentelemetry-exporter-otlp-proto-common 1.43.0
opentelemetry-exporter-otlp-proto-grpc 1.43.0
opentelemetry-exporter-otlp-proto-http 1.43.0
opentelemetry-proto 1.43.0
opentelemetry-sdk 1.43.0
opentelemetry-semantic-conventions 0.64b0
opentelemetry-semantic-conventions-ai 0.5.1
outlines-core 0.2.14
packaging 26.2
partial-json-parser 0.2.1.1.post7
pillow 12.3.0
pip 26.1.2
portalocker 3.2.0
prometheus-client 0.25.0
prometheus-fastapi-instrumentator 8.0.2
propcache 0.5.2
protobuf 7.35.1
psutil 7.2.2
py-cpuinfo 9.0.0
pybase64 1.4.3
pycountry 26.2.16
pycparser 3.0
pydantic 2.13.4
pydantic-core 2.46.4
pydantic-extra-types 2.11.1
pydantic-settings 2.14.2
pygments 2.20.0
pyjwt 2.13.0
pymupdf 1.28.0
pypdfium2 5.11.0
python-dotenv 1.2.2
python-json-logger 4.1.0
python-multipart 0.0.32
pyyaml 6.0.3
pyzmq 27.1.0
referencing 0.37.0
regex 2026.6.28
requests 2.34.2
rich 15.0.0
rich-toolkit 0.20.1
rignore 0.7.6
rpds-py 2026.6.3
safetensors 0.8.0
sentencepiece 0.2.1
sentry-sdk 2.64.0
setproctitle 1.3.7
setuptools 77.0.3
shellingham 1.5.4
six 1.17.0
sniffio 1.3.1
sse-starlette 3.4.5
starlette 1.3.1
supervisor 4.3.0
sympy 1.14.0
tiktoken 0.13.0
tokenizers 0.22.2
torch 2.11.0+cpu
torchaudio 2.11.0+cpu
torchvision 0.26.0+cpu
tqdm 4.68.3
transformers 5.13.0
typer 0.26.8
typing-extensions 4.16.0
typing-inspection 0.4.2
urllib3 2.7.0
uvicorn 0.50.0
uvloop 0.22.1
vllm 0.24.0+cpu
watchfiles 1.2.0
websockets 16.0
xgrammar 0.2.3
yarl 1.24.2
(.venv) root@80a09d6d82c7:/# cat /etc/os-release
PRETTY_NAME="Ubuntu 24.04.4 LTS"
NAME="Ubuntu"
VERSION_ID="24.04"
VERSION="24.04.4 LTS (Noble Numbat)"
VERSION_CODENAME=noble
ID=ubuntu
ID_LIKE=debian
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
UBUNTU_CODENAME=noble
LOGO=ubuntu-logo
(.venv) root@80a09d6d82c7:/# Who can help? / 谁可以帮助到您？
No response
Information / 问题信息
- The official example scripts / 官方的示例脚本
- My own modified scripts / 我自己修改的脚本和任务
Reproduction / 复现过程
sudo docker run -it --name vM ubuntu:24.04 bin/bash
export TZ="Europe/Rome"
apt update
apt upgrade -y
apt install -y --no-install-recommends libtcmalloc-minimal4
find / -iname *libtcmalloc_minimal.so.4
TC_PATH=/usr/lib/aarch64-linux-gnu/libtcmalloc_minimal.so.4
export LD_PRELOAD="$TC_PATH:$LD_PRELOAD"
apt install -y pipx
pipx install uv
pipx ensurepat
source ~/.bashrc
uv --version
uv venv --python 3.12 --seed --managed-python
source .venv/bin/activate
apt install -y wget
wget https://github.com/vllm-project/vllm/releases/download/v0.24.0/vllm-0.24.0+cpu-cp38-abi3-manylinux_2_34_aarch64.whl
uv pip install --torch-backend cpu vllm-0.24.0+cpu-cp38-abi3-manylinux_2_34_aarch64.whl
uv pip install "glmocr[selfhosted]"
uv pip install "transformers>=5.3.0"
vllm serve zai-org/GLM-OCR --port 8080 --speculative-config '{"method": "mtp", "num_speculative_tokens": 3}' --served-model-name glm-ocr(.venv) root@80a09d6d82c7:/# vllm serve zai-org/GLM-OCR --port 8080 --speculative-config '{"method": "mtp", "num_speculative_tokens": 3}' --served-model-name glm-ocr
INFO 07-05 14:07:05 [importing.py:81] Triton not installed or not compatible; certain GPU-related functions will not be available.
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:339]
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:339] █ █ █▄ ▄█
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:339] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.24.0
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:339] █▄█▀ █ █ █ █ model zai-org/GLM-OCR
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:339] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:339]
(APIServer pid=408) INFO 07-05 14:07:05 [api_utils.py:273] non-default args: {'model_tag': 'zai-org/GLM-OCR', 'port': 8080, 'model': 'zai-org/GLM-OCR', 'served_model_name': ['glm-ocr'], 'speculative_config': {'method': 'mtp', 'num_speculative_tokens': 3}}
(APIServer pid=408) Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
(APIServer pid=408) INFO 07-05 14:07:07 [model.py:598] Resolved architecture: GlmOcrForConditionalGeneration
(APIServer pid=408) INFO 07-05 14:07:07 [model.py:1725] Using max model len 131072
(APIServer pid=408) INFO 07-05 14:07:09 [model.py:598] Resolved architecture: GlmOcrMTPModel
(APIServer pid=408) INFO 07-05 14:07:09 [model.py:1725] Using max model len 131072
(APIServer pid=408) WARNING 07-05 14:07:09 [speculative.py:761] Enabling num_speculative_tokens > 1 will run multiple times of forward on same MTP layer,which may result in lower acceptance rate
(APIServer pid=408) INFO 07-05 14:07:09 [vllm.py:1006] Asynchronous scheduling is enabled.
(APIServer pid=408) INFO 07-05 14:07:09 [kernel.py:276] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native'])
(APIServer pid=408) WARNING 07-05 14:07:09 [vllm.py:1614] max_num_scheduled_tokens is set to 2048 based on the speculative decoding settings. This may lead to suboptimal performance. Consider increasing max_num_batched_tokens to accommodate the additional draft token slots, or decrease num_speculative_tokens or max_num_seqs.
(APIServer pid=408) WARNING 07-05 14:07:11 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
(APIServer pid=408) WARNING 07-05 14:07:11 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
(APIServer pid=408) WARNING 07-05 14:07:11 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
(APIServer pid=408) WARNING 07-05 14:07:11 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
INFO 07-05 14:07:26 [importing.py:81] Triton not installed or not compatible; certain GPU-related functions will not be available.
(EngineCore pid=440) INFO 07-05 14:07:27 [core.py:114] Initializing a V1 LLM engine (v0.24.0) with config: model='zai-org/GLM-OCR', speculative_config=SpeculativeConfig(method='mtp', model='zai-org/GLM-OCR', num_spec_tokens=3), tokenizer='zai-org/GLM-OCR', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=True, quantization=None, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cpu, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False, jit_monitor_verbose=False), seed=0, served_model_name=glm-ocr, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.DYNAMO_TRACE_ONCE: 2>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none', '+gelu'], 'ir_enable_torch_wrap': False, 'splitting_ops': [], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': None, 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'dce': True, 'nan_asserts': False, 'epilogue_fusion': True, 'cpp.dynamic_threads': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.NONE: 0>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'fuse_rope_kvcache_cat_mla': False, 'fuse_act_padding': False}, 'max_cudagraph_capture_size': None, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}, kernel_config=KernelConfig(ir_op_priority=IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']), enable_flashinfer_autotune=True, moe_backend='auto', linear_backend='auto')
(EngineCore pid=440) INFO 07-05 14:07:27 [multiproc_executor.py:140] DP group leader: node_rank=0, node_rank_within_dp=0, master_addr=127.0.0.1, mq_connect_ip=172.17.0.2 (local), world_size=1, local_world_size=1
(EngineCore pid=440) INFO 07-05 14:07:27 [ompmultiprocessing.py:185] OpenMP thread binding info:
(EngineCore pid=440) INFO 07-05 14:07:27 [ompmultiprocessing.py:185] VLLM_CPU_OMP_THREADS_BIND='auto', auto_setup=True, skip_setup=False
(EngineCore pid=440) INFO 07-05 14:07:27 [ompmultiprocessing.py:185] local_world_size=1, reserve_cpu_num=1
(EngineCore pid=440) INFO 07-05 14:07:27 [ompmultiprocessing.py:185] local_rank=0, core ids=[0, 1, 2, 3, 4, 5, 6]
(EngineCore pid=440) INFO 07-05 14:07:27 [ompmultiprocessing.py:185] reserved_cpus=[7]
INFO 07-05 14:07:31 [importing.py:81] Triton not installed or not compatible; certain GPU-related functions will not be available.
WARNING 07-05 14:07:32 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
WARNING 07-05 14:07:32 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
WARNING 07-05 14:07:32 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
WARNING 07-05 14:07:32 [cpu.py:453] Failed to import from vllm._C: ImportError('libnuma.so.1: cannot open shared object file: No such file or directory')
Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
ERROR 07-05 14:07:36 [multiproc_executor.py:898] WorkerProc failed to start.
ERROR 07-05 14:07:36 [multiproc_executor.py:898] Traceback (most recent call last):
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 865, in worker_main
ERROR 07-05 14:07:36 [multiproc_executor.py:898] worker = WorkerProc(*args, **kwargs)
ERROR 07-05 14:07:36 [multiproc_executor.py:898] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
ERROR 07-05 14:07:36 [multiproc_executor.py:898] return func(*args, **kwargs)
ERROR 07-05 14:07:36 [multiproc_executor.py:898] ^^^^^^^^^^^^^^^^^^^^^
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 618, in __init__
ERROR 07-05 14:07:36 [multiproc_executor.py:898] wrapper.init_worker(all_kwargs)
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
ERROR 07-05 14:07:36 [multiproc_executor.py:898] return func(*args, **kwargs)
ERROR 07-05 14:07:36 [multiproc_executor.py:898] ^^^^^^^^^^^^^^^^^^^^^
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/vllm/v1/worker/worker_base.py", line 319, in init_worker
ERROR 07-05 14:07:36 [multiproc_executor.py:898] self.worker = worker_class(**kwargs)
ERROR 07-05 14:07:36 [multiproc_executor.py:898] ^^^^^^^^^^^^^^^^^^^^^^
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/vllm/v1/worker/cpu_worker.py", line 58, in __init__
ERROR 07-05 14:07:36 [multiproc_executor.py:898] torch.ops._C.init_cpu_memory_env([cpu_core.numa_node])
ERROR 07-05 14:07:36 [multiproc_executor.py:898] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 07-05 14:07:36 [multiproc_executor.py:898] File "/.venv/lib/python3.12/site-packages/torch/_ops.py", line 1379, in __getattr__
ERROR 07-05 14:07:36 [multiproc_executor.py:898] raise AttributeError(
ERROR 07-05 14:07:36 [multiproc_executor.py:898] AttributeError: '_OpNamespace' '_C' object has no attribute 'init_cpu_memory_env'
(EngineCore pid=440) INFO 07-05 14:07:36 [multiproc_executor.py:426] [shutdown] Executor: waiting for worker exit count=1
(EngineCore pid=440) INFO 07-05 14:07:37 [multiproc_executor.py:433] [shutdown] Executor: all workers exited gracefully
(EngineCore pid=440) ERROR 07-05 14:07:37 [core.py:1231] EngineCore failed to start.
(EngineCore pid=440) ERROR 07-05 14:07:37 [core.py:1231] Traceback (most recent call last):
(EngineCore pid=440) ERROR 07-05 14:07:37 [core.py:1231] File "/.venv/lib/python3.12/site-packages/vllSource: zai-org/GLM-OCR