当前环境
The output of `python collect_env.py`
Collecting environment information...
PyTorch version: 2.3.1+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: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.30.1
Libc version: glibc-2.35
Python version: 3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-1053-nvidia-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.2.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3
Nvidia driver version: 550.90.07
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.6
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.6
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: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 224
On-line CPU(s) list: 0-223
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8480C
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 56
Socket(s): 2
Stepping: 8
CPU max MHz: 3800.0000
CPU min MHz: 800.0000
BogoMIPS: 4000.00
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 art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq 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 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 5.3 MiB (112 instances)
L1i cache: 3.5 MiB (112 instances)
L2 cache: 224 MiB (112 instances)
L3 cache: 210 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-55,112-167
NUMA node1 CPU(s): 56-111,168-223
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
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; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] torch==2.3.1
[pip3] torchvision==0.18.1
[pip3] transformers==4.43.1
[pip3] triton==2.3.1
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.3.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 NIC10 NIC11 CPU AffinityNUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PXB NODE NODE NODE NODE NODE SYS SYS SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE NODE NODE PXB NODE NODE SYS SYS SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE NODE NODE PXB NODE SYS SYS SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE NODE NODE PXB SYS SYS SYS SYS SYS SYS 0-55,112-167 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS SYS PXB NODE NODE NODE NODE NODE 56-111,168-223 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS SYS NODE NODE NODE PXB NODE NODE 56-111,168-223 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS NODE NODE NODE NODE PXB NODE 56-111,168-223 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS NODE NODE NODE NODE NODE PXB 56-111,168-223 1 N/A
NIC0 PXB NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE NODE NODE SYS SYS SYS SYS SYS SYS
NIC1 NODE NODE NODE NODE SYS SYS SYS SYS NODE X PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS
NIC2 NODE NODE NODE NODE SYS SYS SYS SYS NODE PIX X NODE NODE NODE SYS SYS SYS SYS SYS SYS
NIC3 NODE PXB NODE NODE SYS SYS SYS SYS NODE NODE NODE X NODE NODE SYS SYS SYS SYS SYS SYS
NIC4 NODE NODE PXB NODE SYS SYS SYS SYS NODE NODE NODE NODE X NODE SYS SYS SYS SYS SYS SYS
NIC5 NODE NODE NODE PXB SYS SYS SYS SYS NODE NODE NODE NODE NODE X SYS SYS SYS SYS SYS SYS
NIC6 SYS SYS SYS SYS PXB NODE NODE NODE SYS SYS SYS SYS SYS SYS X NODE NODE NODE NODE NODE
NIC7 SYS SYS SYS SYS NODE NODE NODE NODE SYS SYS SYS SYS SYS SYS NODE X PIX NODE NODE NODE
NIC8 SYS SYS SYS SYS NODE NODE NODE NODE SYS SYS SYS SYS SYS SYS NODE PIX X NODE NODE NODE
NIC9 SYS SYS SYS SYS NODE PXB NODE NODE SYS SYS SYS SYS SYS SYS NODE NODE NODE X NODE NODE
NIC10 SYS SYS SYS SYS NODE NODE PXB NODE SYS SYS SYS SYS SYS SYS NODE NODE NODE NODE X NODE
NIC11 SYS SYS SYS SYS NODE NODE NODE PXB SYS SYS SYS SYS SYS SYS NODE NODE NODE NODE NODE X
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
NIC Legend:
NIC0: mlx5_0
NIC1: mlx5_1
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
NIC6: mlx5_6
NIC7: mlx5_7
NIC8: mlx5_8
NIC9: mlx5_9
NIC10: mlx5_10
NIC11: mlx5_11您希望如何使用vllm
我尝试在单台8xH100设备上使用文章中描述的方法加载meta-llama/Meta-Llama-3.1-405B-Instruct-FP8模型。然而，它运行不正确，并返回了以下错误信息：
root@dbe9716daf8891-sz5t2:/workspace# vllm serve /models/Meta-Llama-3.1-405B-Instruct-FP8 --tensor-parallel-size 8 --served-model-name "Meta-Llama-3.1-405B-Instruct-FP8" --gpu-memory-utilization 0.98
INFO 07-24 14:03:05 api_server.py:219] vLLM API server version 0.5.3.post1
INFO 07-24 14:03:05 api_server.py:220] args: Namespace(model_tag='/models/Meta-Llama-3.1-405B-Instruct-FP8', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, 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='/models/Meta-Llama-3.1-405B-Instruct-FP8', tokenizer=None, 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='auto', kv_cache_dtype='auto', quantization_param_path=None, max_model_len=None, guided_decoding_backend='outlines', distributed_executor_backend=None, worker_use_ray=False, pipeline_parallel_size=1, tensor_parallel_size=8, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=16, enable_prefix_caching=False, disable_sliding_window=False, use_v2_block_manager=False, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.98, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=256, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, enforce_eager=False, max_context_len_to_capture=None, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, enable_lora=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, num_speculative_tokens=None, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['Meta-Llama-3.1-405B-Instruct-FP8'], qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, engine_use_ray=False, disable_log_requests=False, max_log_len=None, dispatch_function=<function serve at 0x7fe0c5fee710>)
INFO 07-24 14:03:06 config.py:715] Defaulting to use mp for distributed inference
WARNING 07-24 14:03:06 arg_utils.py:762] Chunked prefill is enabled by default for models with max_model_len > 32K. Currently, chunked prefill might not work with some features or models. If you encounter any issues, please disable chunked prefill by setting --enable-chunked-prefill=False.
INFO 07-24 14:03:06 config.py:806] Chunked prefill is enabled with max_num_batched_tokens=512.
INFO 07-24 14:03:06 llm_engine.py:176] Initializing an LLM engine (v0.5.3.post1) with config: model='/models/Meta-Llama-3.1-405B-Instruct-FP8', speculative_config=None, tokenizer='/models/Meta-Llama-3.1-405B-Instruct-FP8', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, rope_scaling=None, rope_theta=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=131072, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=8, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=fbgemm_fp8, enforce_eager=False, kv_cache_dtype=auto, quantization_param_path=None, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='outlines'), observability_config=ObservabilityConfig(otlp_traces_endpoint=None), seed=0, served_model_name=Meta-Llama-3.1-405B-Instruct-FP8, use_v2_block_manager=False, enable_prefix_caching=False)
INFO 07-24 14:03:06 custom_cache_manager.py:17] Setting Triton cache manager to: vllm.triton_utils.custom_cache_manager:CustomCacheManager
(VllmWorkerProcess pid=6495) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=6499) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=6494) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=6500) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=6498) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=6496) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
(VllmWorkerProcess pid=6497) INFO 07-24 14:03:07 multiproc_worker_utils.py:215] Worker ready; awaiting tasks
INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6498) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6496) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6498) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6496) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6494) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6497) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6499) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6497) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6495) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6494) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6499) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6495) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6500) INFO 07-24 14:03:23 utils.py:784] Found nccl from library libnccl.so.2
(VllmWorkerProcess pid=6500) INFO 07-24 14:03:23 pynccl.py:63] vLLM is using nccl==2.20.5
(VllmWorkerProcess pid=6498) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
(VllmWorkerProcess pid=6499) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
(VllmWorkerProcess pid=6495) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
(VllmWorkerProcess pid=6500) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
(VllmWorkerProcess pid=6497) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
(VllmWorkerProcess pid=6496) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
(VllmWorkerProcess pid=6494) INFO 07-24 14:03:36 custom_all_reduce_utils.py:232] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1,2,3,4,5,6,7.json
INFO 07-24 14:03:36 shm_broadcast.py:241] vLLM message queue communication handle: Handle(connect_ip='127.0.0.1', local_reader_ranks=[1, 2, 3, 4, 5, 6, 7], buffer=<vllm.distributed.device_communicators.shm_broadcast.ShmRingBuffer object at 0x7fe0c4bd3040>, local_subscribe_port=32775, local_sync_port=49501, remote_subscribe_port=None, remote_sync_port=None)
(VllmWorkerProcess pid=6495) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6499) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6500) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6498) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6496) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6497) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6494) INFO 07-24 14:03:36 model_runner.py:680] Starting to load model /models/Meta-Llama-3.1-405B-Instruct-FP8...
(VllmWorkerProcess pid=6494) INFO 07-24 14:07:31 model_runner.py:692] Loading model weights took 57.7520 GB
(VllmWorkerProcess pid=6498) INFO 07-24 14:07:31 model_runner.py:692] Loading model weights took 57.7520 GB
INFO 07-24 14:07:31 model_runner.py:692] Loading model weights took 57.7520 GB
(VllmWorkerProcess pid=6500) INFO 07-24 14:07:31 model_runner.py:692] Loading model weights took 57.7520 GB
(VllmWorkerProcess pid=6497) INFO 07-24 14:07:31 model_runner.py:692] Loading model weights took 57.7520 GB
(VllmWorkerProcess pid=6496) INFO 07-24 14:07:31 model_runner.py:692] Loading model weights took 57.7520 GB
(VllmWorkerProcess pid=6499) INFO 07-24 14:07:32 model_runner.py:692] Loading model weights took 57.7520 GB
(VllmWorkerProcess pid=6495) INFO 07-24 14:07:32 model_runner.py:692] Loading model weights took 57.7520 GB
INFO 07-24 14:07:40 distributed_gpu_executor.py:56] # GPU blocks: 4962, # CPU blocks: 2080
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] Exception in worker VllmWorkerProcess while processing method initialize_cache: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine., Traceback (most recent call last):
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_worker_utils.py", line 223, in _run_worker_process
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] output = executor(*args, **kwargs)
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise_if_cache_size_invalid(num_gpu_blocks,
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise ValueError(
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] Exception in worker VllmWorkerProcess while processing method initialize_cache: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine., Traceback (most recent call last):
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
(VllmWorkerProcess pid=6494) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226]
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_worker_utils.py", line 223, in _run_worker_process
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] output = executor(*args, **kwargs)
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise_if_cache_size_invalid(num_gpu_blocks,
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise ValueError(
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
(VllmWorkerProcess pid=6497) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226]
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] Exception in worker VllmWorkerProcess while processing method initialize_cache: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine., Traceback (most recent call last):
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_worker_utils.py", line 223, in _run_worker_process
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] output = executor(*args, **kwargs)
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise_if_cache_size_invalid(num_gpu_blocks,
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise ValueError(
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
(VllmWorkerProcess pid=6499) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226]
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] Exception in worker VllmWorkerProcess while processing method initialize_cache: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine., Traceback (most recent call last):
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_worker_utils.py", line 223, in _run_worker_process
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] output = executor(*args, **kwargs)
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise_if_cache_size_invalid(num_gpu_blocks,
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise ValueError(
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
(VllmWorkerProcess pid=6500) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226]
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] Exception in worker VllmWorkerProcess while processing method initialize_cache: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine., Traceback (most recent call last):
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_worker_utils.py", line 223, in _run_worker_process
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] output = executor(*args, **kwargs)
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise_if_cache_size_invalid(num_gpu_blocks,
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise ValueError(
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
(VllmWorkerProcess pid=6498) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226]
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] Exception in worker VllmWorkerProcess while processing method initialize_cache: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine., Traceback (most recent call last):
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_worker_utils.py", line 223, in _run_worker_process
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] output = executor(*args, **kwargs)
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise_if_cache_size_invalid(num_gpu_blocks,
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] raise ValueError(
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226] ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
(VllmWorkerProcess pid=6496) ERROR 07-24 14:07:40 multiproc_worker_utils.py:226]
[rank0]: Traceback (most recent call last):
[rank0]: File "/usr/local/bin/vllm", line 8, in <module>
[rank0]: sys.exit(main())
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/scripts.py", line 148, in main
[rank0]: args.dispatch_function(args)
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/scripts.py", line 28, in serve
[rank0]: run_server(args)
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 231, in run_server
[rank0]: if llm_engine is not None else AsyncLLMEngine.from_engine_args(
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 466, in from_engine_args
[rank0]: engine = cls(
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 380, in __init__
[rank0]: self.engine = self._init_engine(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/engine/async_llm_engine.py", line 547, in _init_engine
[rank0]: return engine_class(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 265, in __init__
[rank0]: self._initialize_kv_caches()
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 377, in _initialize_kv_caches
[rank0]: self.model_executor.initialize_cache(num_gpu_blocks, num_cpu_blocks)
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/executor/distributed_gpu_executor.py", line 62, in initialize_cache
[rank0]: self._run_workers("initialize_cache",
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/executor/multiproc_gpu_executor.py", line 178, in _run_workers
[rank0]: driver_worker_output = driver_worker_method(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 212, in initialize_cache
[rank0]: raise_if_cache_size_invalid(num_gpu_blocks,
[rank0]: File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 372, in raise_if_cache_size_invalid
[rank0]: raise ValueError(
[rank0]: ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (79392). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.
ERROR 07-24 14:07:41 multiproc_worker_utils.py:120] Worker VllmWorkerProcess pid 6500 died, exit code: -15
INFO 07-24 14:07:41 multiproc_worker_utils.py:123] Killing local vLLM worker processes
[rank0]:[W CudaIPCTypes.cpp:16] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
/usr/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked shared_memory objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
1条答案
按热度按时间iqih9akk1#
Set
--max-model-len 79392or lower as needed, you do not have enough vram for the full context length