vllm
vllm copied to clipboard
Published
2 months ago
•
vllm-project
vllm-project
[Bug]: `facebook/chameleon-30b` triggers assertion error while loading weights
Your current environment
The output of `python collect_env.py`
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: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: Could not collect
CMake version: version 3.30.2
Libc version: glibc-2.31
Python version: 3.10.14 (main, Apr 6 2024, 18:45:05) [GCC 9.4.0] (64-bit runtime)
Python platform: Linux-6.5.0-1023-aws-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A100-SXM4-40GB
GPU 1: NVIDIA A100-SXM4-40GB
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) Platinum 8275CL CPU @ 3.00GHz
Stepping: 7
CPU MHz: 1257.578
BogoMIPS: 5999.99
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 1.5 MiB
L1i cache: 1.5 MiB
L2 cache: 48 MiB
L3 cache: 71.5 MiB
NUMA node0 CPU(s): 0-23,48-71
NUMA node1 CPU(s): 24-47,72-95
Vulnerability Gather data sampling: Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit: KVM: Mitigation: VMX unsupported
Vulnerability L1tf: Mitigation; PTE Inversion
Vulnerability Mds: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed: Vulnerable
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Retpoline
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 s
s ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pcl
mulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm ab
m 3dnowprefetch invpcid_single pti fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx avx512f avx512dq rdseed adx smap clflushopt
clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves ida arat pku ospke
Versions of relevant libraries:
[pip3] flashinfer==0.1.2+cu121torch2.4
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] pyzmq==26.1.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.0
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.4
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV12 0-23,48-71 0 N/A
GPU1 NV12 X 0-23,48-71 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
🐛 Describe the bug
Running vLLM v0.5.4 with tensor parallelism degree 2. facebook/chameleon-7b works well (this one with TP 1), but facebook/chameleon-30b fails to load weights while reading in the first safetensors shard. The name of the parameter that triggers the assertion is model.layers.3.self_attn.k_norm.bias.
Traceback (most recent call last):
File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/rpc/server.py", line 217, in run_rpc_server
server = AsyncEngineRPCServer(async_engine_args, usage_context, port)
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/rpc/server.py", line 25, in __init__
self.engine = AsyncLLMEngine.from_engine_args(async_engine_args,
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 484, in from_engine_args
engine = cls(
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 394, in __init__
self.engine = self._init_engine(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 565, in _init_engine
return engine_class(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 274, in __init__
self.model_executor = executor_class(
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_gpu_executor.py", line 215, in __init__
super().__init__(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/distributed_gpu_executor.py", line 25, in __init__
super().__init__(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/executor_base.py", line 47, in __init__
self._init_executor()
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_gpu_executor.py", line 138, in _init_executor
self._run_workers("load_model",
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_gpu_executor.py", line 192, in _run_workers
driver_worker_output = driver_worker_method(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 139, in load_model
self.model_runner.load_model()
File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 722, in load_model
self.model = get_model(model_config=self.model_config,
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/__init__.py", line 21, in get_model
return loader.load_model(model_config=model_config,
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/loader.py", line 327, in load_model
model.load_weights(
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/chameleon.py", line 1048, in load_weights
weight_loader(param, loaded_weight)
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/weight_utils.py", line 470, in default_weight_loader
assert param.size() == loaded_weight.size()
AssertionError
Loading safetensors checkpoint shards: 0% Completed | 0/15 [00:00<?, ?it/s]
