Your current environment

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 20.04.2 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: Could not collect
CMake version: version 3.29.2
Libc version: glibc-2.31

Python version: 3.9.19 (main, Mar 21 2024, 17:11:28)  [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-92-generic-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.1.66
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA RTX A6000
GPU 1: NVIDIA RTX A6000
GPU 2: NVIDIA RTX A6000
GPU 3: NVIDIA RTX A6000
GPU 4: NVIDIA RTX A6000
GPU 5: NVIDIA RTX A6000
GPU 6: NVIDIA RTX A6000
GPU 7: NVIDIA RTX A6000

Nvidia driver version: 535.54.03
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):                             96
On-line CPU(s) list:                0-95
Thread(s) per core:                 2
Core(s) per socket:                 24
Socket(s):                          2
NUMA node(s):                       2
Vendor ID:                          GenuineIntel
CPU family:                         6
Model:                              85
Model name:                         Intel(R) Xeon(R) Gold 5220R CPU @ 2.20GHz
Stepping:                           7
CPU MHz:                            2200.000
CPU max MHz:                        4000.0000
CPU min MHz:                        1000.0000
BogoMIPS:                           4400.00
Virtualization:                     VT-x
L1d cache:                          1.5 MiB
L1i cache:                          1.5 MiB
L2 cache:                           48 MiB
L3 cache:                           71.5 MiB
NUMA node0 CPU(s):                  0-23,48-71
NUMA node1 CPU(s):                  24-47,72-95
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 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 IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
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 pku ospke avx512_vnni md_clear flush_l1d arch_capabilities

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] numpy                     1.26.4                   pypi_0    pypi
[conda] nvidia-nccl-cu12          2.19.3                   pypi_0    pypi
[conda] torch                     2.2.1                    pypi_0    pypi
[conda] triton                    2.2.0                    pypi_0    pypi
[conda] vllm-nccl-cu12            2.18.1.0.3.0             pypi_0    pypiROCM 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    GPU4    GPU5    GPU6    GPU7    CPU Affinity    NUMA Affinity GPU NUMA ID
GPU0     X      PIX     NODE    NODE    SYS     SYS     SYS     SYS     0-23,48-71      0     N/A
GPU1    PIX      X      NODE    NODE    SYS     SYS     SYS     SYS     0-23,48-71      0     N/A
GPU2    NODE    NODE     X      PIX     SYS     SYS     SYS     SYS     0-23,48-71      0     N/A
GPU3    NODE    NODE    PIX      X      SYS     SYS     SYS     SYS     0-23,48-71      0     N/A
GPU4    SYS     SYS     SYS     SYS      X      PIX     NODE    NODE    24-47,72-95     1     N/A
GPU5    SYS     SYS     SYS     SYS     PIX      X      NODE    NODE    24-47,72-95     1     N/A
GPU6    SYS     SYS     SYS     SYS     NODE    NODE     X      PIX     24-47,72-95     1     N/A
GPU7    SYS     SYS     SYS     SYS     NODE    NODE    PIX      X      24-47,72-95     1     N/A

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

🐛 Describe the bug

CUDA_VISIBLE_DEVICES=2,6,1,0 python -O -u -m vllm.entrypoints.openai.api_server \
        --host=127.0.0.1 \
        --port=8090 \
        --model=llama3-70B/ \
        --tokenizer=meta-llama/Meta-Llama-3-70B-Instruct \
        --tensor-parallel-size=4 \
        --quantization fp8 \
        --dtype half

And the error is
ValueError: The quantization method fp8 is not supported for the current GPU. Minimum capability: 90. Current capability: 86.
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] Error executing method load_model. This might cause deadlock in distributed execution.
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] Traceback (most recent call last):
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/worker/worker_base.py", line 149, in execute_method
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] return executor(*args, **kwargs)
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/worker/worker.py", line 117, in load_model
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] self.model_runner.load_model()
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/worker/model_runner.py", line 162, in load_model
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] self.model = get_model(
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/init.py", line 19, in get_model
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] return loader.load_model(model_config=model_config,
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/loader.py", line 222, in load_model
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] model = _initialize_model(model_config, self.load_config,
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/loader.py", line 88, in _initialize_model
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] linear_method = _get_linear_method(model_config, load_config)
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/loader.py", line 47, in _get_linear_method
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] raise ValueError(
(RayWorkerWrapper pid=2202490) ERROR 04-24 16:06:40 worker_base.py:157] ValueError: The quantization method fp8 is not supported for the current GPU. Minimum capability: 90. Current capability: 86.
(RayWorkerWrapper pid=2202821) INFO 04-24 16:06:36 pynccl_utils.py:43] vLLM is using nccl==2.18.1 [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) WARNING 04-24 16:06:39 custom_all_reduce.py:65] Custom allreduce is disabled because it's not supported on more than two PCIe-only GPUs. To silence this warning, specify disable_custom_all_reduce=True explicitly. [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] Error executing method load_model. This might cause deadlock in distributed execution. [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] Traceback (most recent call last): [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/worker/worker_base.py", line 149, in execute_method [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] return executor(*args, **kwargs) [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/loader.py", line 222, in load_model [repeated 6x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] self.model_runner.load_model() [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] self.model = get_model( [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/init.py", line 19, in get_model [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) ERROR 04-24 16:06:40 worker_base.py:157] return loader.load_model(model_config=model_config, [repeated 2x across cluster]

(RayWorkerWrapper pid=2202821) 错误 04-24 16:06:40 worker_base.py:157] model = _initialize_model(model_config, self.load_config, [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) 错误 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/loader.py", line 88, in _initialize_model [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) 错误 04-24 16:06:40 worker_base.py:157] linear_method = _get_linear_method(model_config, load_config) [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) 错误 04-24 16:06:40 worker_base.py:157] File "/data/tianyuhang/.conda/envs/llama3/lib/python3.9/site-packages/vllm/model_executor/model_loader/loader.py", line 47, in _get_linear_method [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) 错误 04-24 16:06:40 worker_base.py:157] raise ValueError( [repeated 2x across cluster]
(RayWorkerWrapper pid=2202821) 错误 04-24 16:06:40 worker_base.py:157] ValueError: The quantization method fp8 is not supported for the current GPU. Minimum capability: 90. Current capability: 86. [repeated 2x across cluster]