Your current environment
The output of `python collect_env.py`
# For security purposes, please feel free to check the contents of collect_env.py before running it.
python collect_env.py
--2024-04-01 08:16:40-- https://raw.githubusercontent.com/vllm-project/vllm/main/collect_env.py
正在解析主机 raw.githubusercontent.com (raw.githubusercontent.com)... 2606:50c0:8003::154, 2606:50c0:8002::154, 2606:50c0:8001::154, ...
正在连接 raw.githubusercontent.com (raw.githubusercontent.com)|2606:50c0:8003::154|:443... 已连接。
已发出 HTTP 请求,正在等待回应... 200 OK
长度: 24853 (24K) [text/plain]
正在保存至: ‘collect_env.py’
collect_env.py 100%[===============================================================>] 24.27K 110KB/s 用时 0.2s
2024-04-01 08:16:41 (110 KB/s) - 已保存 ‘collect_env.py’ [24853/24853])
Collecting environment information...
PyTorch version: 2.1.2+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.29.0
Libc version: glibc-2.35
Python version: 3.9.19 (main, Mar 21 2024, 17:11:28) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.5.0-26-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 11.5.119
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 2080 Ti
GPU 1: NVIDIA GeForce RTX 2080 Ti
GPU 2: NVIDIA GeForce RTX 2080 Ti
GPU 3: NVIDIA GeForce RTX 2080 Ti
Nvidia driver version: 535.161.07
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
架构: x86_64
CPU 运行模式: 32-bit, 64-bit
Address sizes: 46 bits physical, 48 bits virtual
字节序: Little Endian
CPU: 56
在线 CPU 列表: 0-55
厂商 ID: GenuineIntel
型号名称: Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz
CPU 系列: 6
型号: 79
每个核的线程数: 2
每个座的核数: 14
座: 2
步进: 1
CPU 最大 MHz: 3300.0000
CPU 最小 MHz: 1200.0000
BogoMIPS: 4800.24
标记: 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 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 vnmi md_clear flush_l1d
虚拟化: VT-x
L1d 缓存: 896 KiB (28 instances)
L1i 缓存: 896 KiB (28 instances)
L2 缓存: 7 MiB (28 instances)
L3 缓存: 70 MiB (2 instances)
NUMA 节点: 2
NUMA 节点0 CPU: 0-13,28-41
NUMA 节点1 CPU: 14-27,42-55
Vulnerability Gather data sampling: Not affected
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 Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
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, IBRS_FW, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] torch==2.1.2
[pip3] triton==2.1.0
[conda] numpy 1.26.4 pypi_0 pypi
[conda] torch 2.1.2 pypi_0 pypi
[conda] triton 2.1.0 pypi_0 pypiROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.4.0
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV2 SYS SYS 0-13,28-41 0 N/A
GPU1 NV2 X SYS SYS 0-13,28-41 0 N/A
GPU2 SYS SYS X NV2 14-27,42-55 1 N/A
GPU3 SYS SYS NV2 X 14-27,42-55 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
INFO 04-01 08:19:19 model_runner.py:104] Loading model weights took 0.2389 GB
INFO 04-01 08:19:20 gpu_executor.py:94] # GPU blocks: 33910, # CPU blocks: 7281
INFO 04-01 08:19:23 model_runner.py:791] Capturing the model for CUDA graphs. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI.
INFO 04-01 08:19:23 model_runner.py:795] CUDA graphs can take additional 1~3 GiB memory per GPU. If you are running out of memory, consider decreasing `gpu_memory_utilization` or enforcing eager mode. You can also reduce the `max_num_seqs` as needed to decrease memory usage.
Traceback (most recent call last):
File "/home/czb/src/czb/vllm_test.py", line 11, in <module>
llm = LLM(model="facebook/opt-125m")
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/entrypoints/llm.py", line 112, in __init__
self.llm_engine = LLMEngine.from_engine_args(
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/engine/llm_engine.py", line 192, in from_engine_args
engine = cls(
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/engine/llm_engine.py", line 111, in __init__
self.model_executor = executor_class(model_config, cache_config,
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/executor/gpu_executor.py", line 40, in __init__
self._init_cache()
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/executor/gpu_executor.py", line 107, in _init_cache
self.driver_worker.warm_up_model()
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/worker/worker.py", line 167, in warm_up_model
self.model_runner.capture_model(self.gpu_cache)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/worker/model_runner.py", line 854, in capture_model
graph_runner.capture(
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/worker/model_runner.py", line 906, in capture
self.model(
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/model_executor/models/opt.py", line 301, in forward
hidden_states = self.model(input_ids, positions, kv_caches,
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/model_executor/models/opt.py", line 276, in forward
return self.decoder(input_ids, positions, kv_caches, attn_metadata)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/model_executor/models/opt.py", line 250, in forward
hidden_states = layer(hidden_states, kv_caches[i], attn_metadata)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/model_executor/models/opt.py", line 158, in forward
hidden_states = self.self_attn(hidden_states=hidden_states,
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/model_executor/models/opt.py", line 103, in forward
output, _ = self.out_proj(attn_output)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/czb/miniconda3/envs/vllm/lib/python3.9/site-packages/vllm/model_executor/layers/linear.py", line 580, in forward
output = output_ + self.bias if self.bias is not None else output_
RuntimeError: CUDA error: no kernel image is available for execution on the device
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.
@chuanzhubin @GennVa we just release
v0.4.0.post1to add support for sm 70 and sm75, can you have a try? It’s in https://github.com/vllm-project/vllm/releases/tag/v0.4.0.post1