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: 3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-100-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 3090
GPU 1: NVIDIA GeForce RTX 3090
GPU 2: NVIDIA GeForce RTX 3090
GPU 3: NVIDIA GeForce RTX 3090
Nvidia driver version: 535.161.07
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.0
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: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 88
On-line CPU(s) list: 0-87
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) CPU E5-2696 v4 @ 2.20GHz
CPU family: 6
Model: 79
Thread(s) per core: 2
Core(s) per socket: 22
Socket(s): 2
Stepping: 1
CPU max MHz: 3700.0000
CPU min MHz: 1200.0000
BogoMIPS: 4399.70
Flags: 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 vnmi 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 md_clear flush_l1d
Virtualization: VT-x
L1d cache: 1.4 MiB (44 instances)
L1i cache: 1.4 MiB (44 instances)
L2 cache: 11 MiB (44 instances)
L3 cache: 110 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-21,44-65
NUMA node1 CPU(s): 22-43,66-87
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 and seccomp
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 PHB SYS SYS 0-21,44-65 0 N/A
GPU1 PHB X SYS SYS 0-21,44-65 0 N/A
GPU2 SYS SYS X PHB 22-43,66-87 1 N/A
GPU3 SYS SYS PHB X 22-43,66-87 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
INFO 04-02 09:47:24 api_server.py:148] vLLM API server version 0.4.0
INFO 04-02 09:47:24 api_server.py:149] args: Namespace(host='0.0.0.0', port=8001, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, served_model_name='FUX14B2', lora_modules=[LoRA(name='lora_1', local_path='/home/greatwall/app/edison/output/qwen1half-14b-chat/v25-20240330-131708/checkpoint-300'), LoRA(name='lora_2', local_path='/home/greatwall/app/edison/output/qwen1half-14b-chat/v25-20240330-131708/checkpoint-270'), LoRA(name='lora_3', local_path='/home/greatwall/app/edison/output/qwen1half-14b-chat/v25-20240330-131708/checkpoint-240')], chat_template=None, response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], model='/home/greatwall/app/edison/models/Qwen1.5-14B-Chat', tokenizer=None, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, download_dir=None, load_format='auto', dtype='auto', kv_cache_dtype='auto', max_model_len=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=4, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=16, enable_prefix_caching=False, use_v2_block_manager=False, num_lookahead_slots=0, seed=0, swap_space=4, gpu_memory_utilization=1.0, forced_num_gpu_blocks=None, max_num_batched_tokens=None, max_num_seqs=256, max_logprobs=5, disable_log_stats=False, quantization=None, enforce_eager=False, max_context_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, enable_lora=True, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', max_cpu_loras=None, device='auto', image_input_type=None, image_token_id=None, image_input_shape=None, image_feature_size=None, scheduler_delay_factor=0.0, enable_chunked_prefill=False, engine_use_ray=False, disable_log_requests=False, max_log_len=None)
2024-04-02 09:47:26,188 INFO worker.py:1752 -- Started a local Ray instance.
INFO 04-02 09:47:27 llm_engine.py:75] Initializing an LLM engine (v0.4.0) with config: model='/home/greatwall/app/edison/models/Qwen1.5-14B-Chat', tokenizer='/home/greatwall/app/edison/models/Qwen1.5-14B-Chat', tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=4, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, seed=0)
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
INFO 04-02 09:47:45 selector.py:51] Cannot use FlashAttention because the package is not found. Please install it for better performance.
INFO 04-02 09:47:45 selector.py:25] Using XFormers backend.
(RayWorkerVllm pid=43202) INFO 04-02 09:47:45 selector.py:51] Cannot use FlashAttention because the package is not found. Please install it for better performance.
(RayWorkerVllm pid=43202) INFO 04-02 09:47:45 selector.py:25] Using XFormers backend.
(RayWorkerVllm pid=43317) INFO 04-02 09:47:46 pynccl_utils.py:45] vLLM is using nccl==2.18.1
INFO 04-02 09:47:46 pynccl_utils.py:45] vLLM is using nccl==2.18.1
WARNING 04-02 09:47:48 custom_all_reduce.py:45] Custom allreduce is disabled because your platform lacks GPU P2P capability or P2P test failed. To silence this warning, specify disable_custom_all_reduce=True explicitly.
(RayWorkerVllm pid=43202) WARNING 04-02 09:47:48 custom_all_reduce.py:45] Custom allreduce is disabled because your platform lacks GPU P2P capability or P2P test failed. To silence this warning, specify disable_custom_all_reduce=True explicitly.
INFO 04-02 09:47:54 model_runner.py:104] Loading model weights took 6.6485 GB
(RayWorkerVllm pid=43202) INFO 04-02 09:47:56 model_runner.py:104] Loading model weights took 6.6485 GB
(RayWorkerVllm pid=43395) INFO 04-02 09:47:45 selector.py:51] Cannot use FlashAttention because the package is not found. Please install it for better performance. [repeated 2x across cluster] (Ray deduplicates logs by default. Set RAY_DEDUP_LOGS=0 to disable log deduplication, or see https://docs.ray.io/en/master/ray-observability/ray-logging.html#log-deduplication for more options.)
(RayWorkerVllm pid=43395) INFO 04-02 09:47:45 selector.py:25] Using XFormers backend. [repeated 2x across cluster]
(RayWorkerVllm pid=43202) INFO 04-02 09:47:46 pynccl_utils.py:45] vLLM is using nccl==2.18.1 [repeated 2x across cluster]
(RayWorkerVllm pid=43395) WARNING 04-02 09:47:48 custom_all_reduce.py:45] Custom allreduce is disabled because your platform lacks GPU P2P capability or P2P test failed. To silence this warning, specify disable_custom_all_reduce=True explicitly. [repeated 2x across cluster]
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] Error executing method profile_num_available_blocks. This might cause deadlock in distributed execution.
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] Traceback (most recent call last):
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/engine/ray_utils.py", line 37, in execute_method
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return executor(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return func(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/worker/worker.py", line 131, in profile_num_available_blocks
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] self.model_runner.profile_run()
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return func(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/worker/model_runner.py", line 742, in profile_run
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] self.execute_model(seqs, kv_caches)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return func(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/worker/model_runner.py", line 663, in execute_model
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] hidden_states = model_executable(**execute_model_kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return self._call_impl(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return forward_call(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/model_executor/models/qwen2.py", line 317, in forward
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] hidden_states = self.model(input_ids, positions, kv_caches,
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return self._call_impl(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return forward_call(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/model_executor/models/qwen2.py", line 254, in forward
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] hidden_states, residual = layer(
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return self._call_impl(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return forward_call(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/model_executor/models/qwen2.py", line 217, in forward
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] hidden_states = self.mlp(hidden_states)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return self._call_impl(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return forward_call(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/model_executor/models/qwen2.py", line 76, in forward
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] gate_up, _ = self.gate_up_proj(x)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return self._call_impl(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/opt/conda/envs/vllm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] return forward_call(*args, **kwargs)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/lora/layers.py", line 395, in forward
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] output_parallel = self.apply_weights(input_, bias)
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/lora/layers.py", line 509, in apply_weights
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] _apply_lora_packed_nslice(
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/lora/layers.py", line 97, in _apply_lora_packed_nslice
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] add_lora_slice(output, x, lora_a_stacked[slice_idx],
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] File "/home/greatwall/app/edison/vllm/vllm/lora/punica.py", line 160, in add_lora_slice
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] punica_kernels.dispatch_bgmv_low_level(
(RayWorkerVllm pid=43395) ERROR 04-02 09:47:57 ray_utils.py:44] RuntimeError: No suitable kernel. h_in=16 h_out=3424 dtype=Float out_dtype=BFloat16
