当前环境

The output of `python collect_env.py`

Collecting environment information...
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: Could not collect
Clang version: Could not collect
CMake version: version 3.29.2
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.10.213-201.855.amzn2.x86_64-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: Tesla V100-SXM2-16GB
GPU 1: Tesla V100-SXM2-16GB
GPU 2: Tesla V100-SXM2-16GB
GPU 3: Tesla V100-SXM2-16GB

Nvidia driver version: 535.161.08
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
Address sizes:                      46 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             32
On-line CPU(s) list:                0-31
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
CPU family:                         6
Model:                              79
Thread(s) per core:                 2
Core(s) per socket:                 16
Socket(s):                          1
Stepping:                           1
CPU max MHz:                        3000.0000
CPU min MHz:                        1200.0000
BogoMIPS:                           4600.04
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
Hypervisor vendor:                  Xen
Virtualization type:                full
L1d cache:                          512 KiB (16 instances)
L1i cache:                          512 KiB (16 instances)
L2 cache:                           4 MiB (16 instances)
L3 cache:                           45 MiB (1 instance)
NUMA node(s):                       1
NUMA node0 CPU(s):                  0-31
Vulnerability Gather data sampling: Not affected
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:             Not affected
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
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.19.3
[pip3] torch==2.2.1
[pip3] triton==2.2.0
[pip3] vllm-nccl-cu12==2.18.1.0.3.0
[conda] Could not collectROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.4.1
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 	NV1	NV1	NV2	0-31	0		N/A
GPU1	NV1	 X 	NV2	NV1	0-31	0		N/A
GPU2	NV1	NV2	 X 	NV2	0-31	0		N/A
GPU3	NV2	NV1	NV2	 X 	0-31	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

您希望如何使用vllm

大家好，
我正在尝试部署一个经过微调的模型([TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](TheBloke/Mistral-7B-Instruct-v0.2-GPTQ · Hugging Face)),遇到了一些问题。
如果你们能帮我解决这个问题，我会非常感激。
错误信息：

+ python3 -m vllm.entrypoints.openai.api_server --tensor-parallel-size 4 --worker-use-ray --host 0.0.0.0 --port 8080 --model TheBloke/Mistral-7B-Instruct-v0.2-GPTQ --served-model-name mistral --dtype float16 --tokenizer TheBloke/Mistral-7B-Instruct-v0.2-GPTQ --enable-lora --lora-modules tuned-model=/model/v1 -q gptq
INFO 05-08 00:44:27 api_server.py:151] vLLM API server version 0.4.1
INFO 05-08 00:44:27 api_server.py:152] args: Namespace(host='0.0.0.0', port=8080, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, served_model_name=['mistral'], lora_modules=[LoRA(name='tuned-model', local_path='/model/v1')], 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='TheBloke/Mistral-7B-Instruct-v0.2-GPTQ', tokenizer='TheBloke/Mistral-7B-Instruct-v0.2-GPTQ', skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, download_dir=None, load_format='auto', dtype='float16', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=None, guided_decoding_backend='outlines', worker_use_ray=True, 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=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=256, max_logprobs=5, disable_log_stats=False, quantization='gptq', 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, speculative_model=None, num_speculative_tokens=None, speculative_max_model_len=None, model_loader_extra_config=None, engine_use_ray=False, disable_log_requests=False, max_log_len=None)
WARNING 05-08 00:44:28 config.py:1011] Casting torch.bfloat16 to torch.float16.
WARNING 05-08 00:44:28 config.py:169] gptq quantization is not fully optimized yet. The speed can be slower than non-quantized models.
2024-05-08 00:44:30,137	INFO worker.py:1749 -- Started a local Ray instance.
INFO 05-08 00:44:31 llm_engine.py:98] Initializing an LLM engine (v0.4.1) with config: model='TheBloke/Mistral-7B-Instruct-v0.2-GPTQ', speculative_config=None, tokenizer='TheBloke/Mistral-7B-Instruct-v0.2-GPTQ', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.float16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=4, disable_custom_all_reduce=False, quantization=gptq, enforce_eager=False, kv_cache_dtype=auto, quantization_param_path=None, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='outlines'), seed=0)
INFO 05-08 00:44:42 utils.py:608] Found nccl from library /root/.config/vllm/nccl/cu12/libnccl.so.2.18.1
(RayWorkerWrapper pid=2115) INFO 05-08 00:44:42 utils.py:608] Found nccl from library /root/.config/vllm/nccl/cu12/libnccl.so.2.18.1
INFO 05-08 00:44:42 selector.py:65] Cannot use FlashAttention backend for Volta and Turing GPUs.
INFO 05-08 00:44:42 selector.py:33] Using XFormers backend.
(RayWorkerWrapper pid=2115) INFO 05-08 00:44:42 selector.py:65] Cannot use FlashAttention backend for Volta and Turing GPUs.
(RayWorkerWrapper pid=2115) INFO 05-08 00:44:42 selector.py:33] Using XFormers backend.
INFO 05-08 00:44:44 pynccl_utils.py:43] vLLM is using nccl==2.18.1
(RayWorkerWrapper pid=2115) INFO 05-08 00:44:44 pynccl_utils.py:43] vLLM is using nccl==2.18.1
INFO 05-08 00:44:49 utils.py:115] generating GPU P2P access cache for in /root/.config/vllm/gpu_p2p_access_cache_for_0,1,2,3.json
INFO 05-08 00:44:50 utils.py:129] reading GPU P2P access cache from /root/.config/vllm/gpu_p2p_access_cache_for_0,1,2,3.json
(RayWorkerWrapper pid=2115) INFO 05-08 00:44:50 utils.py:129] reading GPU P2P access cache from /root/.config/vllm/gpu_p2p_access_cache_for_0,1,2,3.json
(RayWorkerWrapper pid=2273) INFO 05-08 00:44:42 utils.py:608] Found nccl from library /root/.config/vllm/nccl/cu12/libnccl.so.2.18.1 [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/user-guides/configure-logging.html#log-deduplication for more options.)
(RayWorkerWrapper pid=2273) INFO 05-08 00:44:42 selector.py:65] Cannot use FlashAttention backend for Volta and Turing GPUs. [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) INFO 05-08 00:44:42 selector.py:33] Using XFormers backend. [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) INFO 05-08 00:44:44 pynccl_utils.py:43] vLLM is using nccl==2.18.1 [repeated 2x across cluster]
INFO 05-08 00:44:51 weight_utils.py:193] Using model weights format ['*.safetensors']
(RayWorkerWrapper pid=2115) INFO 05-08 00:44:51 weight_utils.py:193] Using model weights format ['*.safetensors']
INFO 05-08 00:45:02 model_runner.py:173] Loading model weights took 1.0413 GB
(RayWorkerWrapper pid=2115) INFO 05-08 00:45:03 model_runner.py:173] Loading model weights took 1.0413 GB
(RayWorkerWrapper pid=2273) INFO 05-08 00:44:50 utils.py:129] reading GPU P2P access cache from /root/.config/vllm/gpu_p2p_access_cache_for_0,1,2,3.json [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) INFO 05-08 00:44:51 weight_utils.py:193] Using model weights format ['*.safetensors'] [repeated 2x across cluster]
ERROR 05-08 00:45:04 worker_base.py:157] Error executing method determine_num_available_blocks. This might cause deadlock in distributed execution.
ERROR 05-08 00:45:04 worker_base.py:157] Traceback (most recent call last):
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker_base.py", line 149, in execute_method
ERROR 05-08 00:45:04 worker_base.py:157]     return executor(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 138, in determine_num_available_blocks
ERROR 05-08 00:45:04 worker_base.py:157]     self.model_runner.profile_run()
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 927, in profile_run
ERROR 05-08 00:45:04 worker_base.py:157]     self.execute_model(seqs, kv_caches)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 848, in execute_model
ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = model_executable(**execute_model_kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 360, in forward
ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = self.model(input_ids, positions, kv_caches,
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 286, in forward
ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states, residual = layer(
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 224, in forward
ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = self.input_layernorm(hidden_states)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/layernorm.py", line 59, in forward
ERROR 05-08 00:45:04 worker_base.py:157]     out = torch.empty_like(x)
ERROR 05-08 00:45:04 worker_base.py:157] RuntimeError: CUDA error: no kernel image is available for execution on the device
ERROR 05-08 00:45:04 worker_base.py:157] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
ERROR 05-08 00:45:04 worker_base.py:157] For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
ERROR 05-08 00:45:04 worker_base.py:157] Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
ERROR 05-08 00:45:04 worker_base.py:157]
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 159, in <module>
    engine = AsyncLLMEngine.from_engine_args(
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 361, in from_engine_args
    engine = cls(
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 319, in __init__
    self.engine = self._init_engine(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 437, in _init_engine
    return engine_class(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 160, in __init__
    self._initialize_kv_caches()
  File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 236, in _initialize_kv_caches
    self.model_executor.determine_num_available_blocks())
  File "/usr/local/lib/python3.10/dist-packages/vllm/executor/ray_gpu_executor.py", line 199, in determine_num_available_blocks
    num_blocks = self._run_workers("determine_num_available_blocks", )
  File "/usr/local/lib/python3.10/dist-packages/vllm/executor/ray_gpu_executor.py", line 318, in _run_workers
    driver_worker_output = self.driver_worker.execute_method(
  File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker_base.py", line 158, in execute_method
    raise e
  File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker_base.py", line 149, in execute_method
    return executor(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 138, in determine_num_available_blocks
    self.model_runner.profile_run()
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 927, in profile_run
    self.execute_model(seqs, kv_caches)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 848, in execute_model
    hidden_states = model_executable(**execute_model_kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 360, in forward
    hidden_states = self.model(input_ids, positions, kv_caches,
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 286, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 224, in forward
    hidden_states = self.input_layernorm(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/layernorm.py", line 59, in forward
    out = torch.empty_like(x)
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.

(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157] Error executing method determine_num_available_blocks. This might cause deadlock in distributed execution.
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157] Traceback (most recent call last):
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker_base.py", line 149, in execute_method
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return executor(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 138, in determine_num_available_blocks
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     self.model_runner.profile_run()
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 927, in profile_run
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     self.execute_model(seqs, kv_caches)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 848, in execute_model
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = model_executable(**execute_model_kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 360, in forward
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = self.model(input_ids, positions, kv_caches,
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 286, in forward
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states, residual = layer(
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/llama.py", line 224, in forward
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = self.input_layernorm(hidden_states)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/layernorm.py", line 59, in forward
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]     out = torch.empty_like(x)
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157] RuntimeError: CUDA error: no kernel image is available for execution on the device
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157] For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157] Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
(RayWorkerWrapper pid=2115) ERROR 05-08 00:45:04 worker_base.py:157]
(RayWorkerWrapper pid=2211) INFO 05-08 00:45:03 model_runner.py:173] Loading model weights took 1.0413 GB [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157] Error executing method determine_num_available_blocks. This might cause deadlock in distributed execution. [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157] Traceback (most recent call last): [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker_base.py", line 149, in execute_method [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     return executor(*args, **kwargs) [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context [repeated 6x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     return func(*args, **kwargs) [repeated 6x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 138, in determine_num_available_blocks [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     self.model_runner.profile_run() [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 927, in profile_run [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     self.execute_model(seqs, kv_caches) [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/worker/model_runner.py", line 848, in execute_model [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = model_executable(**execute_model_kwargs) [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl [repeated 8x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     return self._call_impl(*args, **kwargs) [repeated 8x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1520, in _call_impl [repeated 8x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     return forward_call(*args, **kwargs) [repeated 8x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]   File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/layernorm.py", line 59, in forward [repeated 8x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = self.model(input_ids, positions, kv_caches, [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states, residual = layer( [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     hidden_states = self.input_layernorm(hidden_states) [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]     out = torch.empty_like(x) [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157] RuntimeError: CUDA error: no kernel image is available for execution on the device [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157] For debugging consider passing CUDA_LAUNCH_BLOCKING=1. [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157] Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. [repeated 2x across cluster]
(RayWorkerWrapper pid=2273) ERROR 05-08 00:45:04 worker_base.py:157]  [repeated 2x across cluster]
[W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]