当前环境

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 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 3.29.3
Libc version: glibc-2.31

Python version: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-117-generic-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA A100 80GB PCIe
GPU 1: NVIDIA A100 80GB PCIe
GPU 2: NVIDIA A100 80GB PCIe
GPU 3: NVIDIA A100 80GB PCIe

Nvidia driver version: 535.183.01
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):                               72
On-line CPU(s) list:                  0-71
Thread(s) per core:                   2
Core(s) per socket:                   18
Socket(s):                            2
NUMA node(s):                         2
Vendor ID:                            GenuineIntel
CPU family:                           6
Model:                                85
Model name:                           Intel(R) Xeon(R) Gold 5220 CPU @ 2.20GHz
Stepping:                             7
CPU MHz:                              2200.000
CPU max MHz:                          3900.0000
CPU min MHz:                          1000.0000
BogoMIPS:                             4400.00
Virtualization:                       VT-x
L1d cache:                            1.1 MiB
L1i cache:                            1.1 MiB
L2 cache:                             36 MiB
L3 cache:                             49.5 MiB
NUMA node0 CPU(s):                    0-17,36-53
NUMA node1 CPU(s):                    18-35,54-71
Vulnerability Gather data sampling:   Mitigation; Microcode
Vulnerability Itlb multihit:          KVM: Mitigation: VMX disabled
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Mitigation; Enhanced IBRS
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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Mitigation; TSX disabled
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 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 intel_ppin 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 mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke avx512_vnni md_clear flush_l1d arch_capabilities

Versions of relevant libraries:
[pip3] flashinfer==0.1.3+cu121torch2.3
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu11==2.20.5
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] onnxruntime==1.18.0
[pip3] optree==0.11.0
[pip3] pytorch_revgrad==0.2.0
[pip3] sentence-transformers==3.0.1
[pip3] torch==2.3.1
[pip3] torchaudio==2.3.1
[pip3] torchvision==0.18.1
[pip3] transformers==4.43.1
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==2.3.1
[conda] flashinfer                0.1.3+cu121torch2.3          pypi_0    pypi
[conda] numpy                     1.26.4                   pypi_0    pypi
[conda] nvidia-nccl-cu11          2.20.5                   pypi_0    pypi
[conda] nvidia-nccl-cu12          2.20.5                   pypi_0    pypi
[conda] optree                    0.11.0                   pypi_0    pypi
[conda] pytorch-cuda              11.8                 h7e8668a_5    pytorch
[conda] pytorch-revgrad           0.2.0                    pypi_0    pypi
[conda] sentence-transformers     3.0.1                    pypi_0    pypi
[conda] torch                     2.3.1                    pypi_0    pypi
[conda] torchaudio                2.3.1                    pypi_0    pypi
[conda] torchvision               0.18.1                   pypi_0    pypi
[conda] transformers              4.43.1                   pypi_0    pypi
[conda] transformers-stream-generator 0.0.5                    pypi_0    pypi
[conda] triton                    2.3.1                    pypi_0    pypi
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    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    SYS     SYS     0-17,36-53      0               N/A
GPU1    NODE     X      SYS     SYS     0-17,36-53      0               N/A
GPU2    SYS     SYS      X      NODE    18-35,54-71     1               N/A
GPU3    SYS     SYS     NODE     X      18-35,54-71     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

🐛 描述bug

from langchain_community.llms import VLLM

llm = VLLM(
    model="/media/user/datadisk/LLM_models/ko-gemma-2-9b-it", 
     # model received from huggingface with the git clone command
    trust_remote_code=True,
    max_new_tokens=4096,
    top_k=3,
    top_p=0.9,
    temperature=0.7,
    
)

你好，我在使用vLLM库加载gemma-2-9b微调模型时发现了一些bug。

1. Please use Flashinfer backend for models with logits_soft_cap (i.e., Gemma-2). Otherwise, the output might be wrong. Set Flashinfer backend by export VLLM_ATTENTION_BACKEND=FLASHINFER. (type=value_error)

上述错误通过如下设置环境变量得到解决。

import os
os.environ['VLLM_ATTENTION_BACKEND'] = 'FLASHINFER'

2. 'NoneType' object is not callable (type=type_error)

上述错误通过安装 flashinfer 库得到解决，详见 #6445 。

从那以后，我遇到了以下问题

[rank0]: Traceback (most recent call last):
[rank0]:   File "/home/user/anaconda3/envs/llm-api/bin/uvicorn", line 8, in <module>
[rank0]:     sys.exit(main())
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
[rank0]:     return self.main(*args, **kwargs)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/click/core.py", line 1078, in main
[rank0]:     rv = self.invoke(ctx)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
[rank0]:     return ctx.invoke(self.callback, **ctx.params)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/click/core.py", line 783, in invoke
[rank0]:     return __callback(*args, **kwargs)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/main.py", line 409, in main
[rank0]:     run(
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/main.py", line 575, in run
[rank0]:     server.run()
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/server.py", line 65, in run
[rank0]:     return asyncio.run(self.serve(sockets=sockets))
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/asyncio/runners.py", line 44, in run
[rank0]:     return loop.run_until_complete(main)
[rank0]:   File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/server.py", line 69, in serve
[rank0]:     await self._serve(sockets)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/server.py", line 76, in _serve
[rank0]:     config.load()
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/config.py", line 433, in load
[rank0]:     self.loaded_app = import_from_string(self.app)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/uvicorn/importer.py", line 19, in import_from_string
[rank0]:     module = importlib.import_module(module_str)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/importlib/__init__.py", line 126, in import_module
[rank0]:     return _bootstrap._gcd_import(name[level:], package, level)
[rank0]:   File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
[rank0]:   File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
[rank0]:   File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked
[rank0]:   File "<frozen importlib._bootstrap>", line 688, in _load_unlocked
[rank0]:   File "<frozen importlib._bootstrap_external>", line 883, in exec_module
[rank0]:   File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
[rank0]:   File "/home/user/Patent-LLM/main.py", line 6, in <module>
[rank0]:     from routers import chat_manager, clear_memory
[rank0]:   File "/home/user/Patent-LLM/routers/clear_memory.py", line 5, in <module>
[rank0]:     from core.get_session import get_user_id
[rank0]:   File "/home/user/Patent-LLM/core/get_session.py", line 8, in <module>
[rank0]:     from core.llm import llm
[rank0]:   File "/home/user/Patent-LLM/core/llm.py", line 16, in <module>
[rank0]:     llm = VLLM(
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/pydantic/v1/main.py", line 339, in __init__
[rank0]:     values, fields_set, validation_error = validate_model(__pydantic_self__.__class__, data)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/pydantic/v1/main.py", line 1048, in validate_model
[rank0]:     input_data = validator(cls_, input_data)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/langchain_core/utils/pydantic.py", line 149, in wrapper
[rank0]:     return func(cls, values)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/langchain_community/llms/vllm.py", line 89, in validate_environment
[rank0]:     values["client"] = VLLModel(
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/entrypoints/llm.py", line 155, in __init__
[rank0]:     self.llm_engine = LLMEngine.from_engine_args(
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/engine/llm_engine.py", line 441, in from_engine_args
[rank0]:     engine = cls(
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/engine/llm_engine.py", line 265, in __init__
[rank0]:     self._initialize_kv_caches()
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/engine/llm_engine.py", line 364, in _initialize_kv_caches
[rank0]:     self.model_executor.determine_num_available_blocks())
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/executor/gpu_executor.py", line 94, in determine_num_available_blocks
[rank0]:     return self.driver_worker.determine_num_available_blocks()
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/worker/worker.py", line 179, in determine_num_available_blocks
[rank0]:     self.model_runner.profile_run()
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/worker/model_runner.py", line 896, in profile_run
[rank0]:     self.execute_model(model_input, kv_caches, intermediate_tensors)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
[rank0]:     return func(*args, **kwargs)
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/worker/model_runner.py", line 1292, in execute_model
[rank0]:     model_input.attn_metadata.begin_forward()
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/vllm/vllm/attention/backends/flashinfer.py", line 146, in begin_forward
[rank0]:     self.prefill_wrapper.begin_forward(
[rank0]:   File "/home/user/anaconda3/envs/llm-api/lib/python3.10/site-packages/flashinfer/prefill.py", line 791, in begin_forward
[rank0]:     self._wrapper.begin_forward(
[rank0]: RuntimeError: CHECK_EQ(paged_kv_indptr.size(0), batch_size + 1) failed. 1 vs 257

我通过vLLM库加载并使用了多个其他模型，但这是我第一次遇到这个问题，而且我没有找到任何关于这个问题的文档。
我尝试(无知地)通过将 batch_size 变量直接设置为256或0来强制大小，但它只改变了两边的vs中的数字。有办法解决这个问题吗？