Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Usage]: Can and How we start server on multi-node multi-gpu with torchrun? #8021

Closed
1 task done
ericxsun opened this issue Aug 30, 2024 · 4 comments
Closed
1 task done

[Usage]: Can and How we start server on multi-node multi-gpu with torchrun? #8021

ericxsun opened this issue Aug 30, 2024 · 4 comments
Labels
usage How to use vllm

Comments

@ericxsun
Copy link

ericxsun commented Aug 30, 2024 •
edited
Loading

Your current environment

Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.1 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.35

Python version: 3.8.19 (default, Mar 20 2024, 19:58:24)  [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-107-generic-x86_64-with-glibc2.17
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H800
GPU 1: NVIDIA H800
GPU 2: NVIDIA H800
GPU 3: NVIDIA H800
GPU 4: NVIDIA H800
GPU 5: NVIDIA H800
GPU 6: NVIDIA H800
GPU 7: NVIDIA H800

Nvidia driver version: 535.161.07
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, 57 bits virtual
Byte Order:                         Little Endian
CPU(s):                             128
On-line CPU(s) list:                0-127
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8462Y+
CPU family:                         6
Model:                              143
Thread(s) per core:                 2
Core(s) per socket:                 32
Socket(s):                          2
Stepping:                           8
CPU max MHz:                        4100.0000
CPU min MHz:                        800.0000
BogoMIPS:                           5600.00
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:                          3 MiB (64 instances)
L1i cache:                          2 MiB (64 instances)
L2 cache:                           128 MiB (64 instances)
L3 cache:                           120 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-31,64-95
NUMA node1 CPU(s):                  32-63,96-127
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; BHI BHI_DIS_S
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

Versions of relevant libraries:
[pip3] numpy==1.24.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.6.20
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.2
[pip3] triton==3.0.0
[conda] numpy                     1.24.4                   pypi_0    pypi
[conda] nvidia-cublas-cu12        12.1.3.1                 pypi_0    pypi
[conda] nvidia-cuda-cupti-cu12    12.1.105                 pypi_0    pypi
[conda] nvidia-cuda-nvrtc-cu12    12.1.105                 pypi_0    pypi
[conda] nvidia-cuda-runtime-cu12  12.1.105                 pypi_0    pypi
[conda] nvidia-cudnn-cu12         9.1.0.70                 pypi_0    pypi
[conda] nvidia-cufft-cu12         11.0.2.54                pypi_0    pypi
[conda] nvidia-curand-cu12        10.3.2.106               pypi_0    pypi
[conda] nvidia-cusolver-cu12      11.4.5.107               pypi_0    pypi
[conda] nvidia-cusparse-cu12      12.1.0.106               pypi_0    pypi
[conda] nvidia-ml-py              12.560.30                pypi_0    pypi
[conda] nvidia-nccl-cu12          2.20.5                   pypi_0    pypi
[conda] nvidia-nvjitlink-cu12     12.6.20                  pypi_0    pypi
[conda] nvidia-nvtx-cu12          12.1.105                 pypi_0    pypi
[conda] pyzmq                     26.2.0                   pypi_0    pypi
[conda] torch                     2.4.0                    pypi_0    pypi
[conda] torchvision               0.19.0                   pypi_0    pypi
[conda] transformers              4.44.2                   pypi_0    pypi
[conda] triton                    3.0.0                    pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.5@09c7792610ada9f88bbf87d32b472dd44bf23cc2
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	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV8	NV8	NV8	NV8	NV8	NV8	NV8	PXB	NODE	NODE	NODE	SYS	SYS	0-31,64-95	0		N/A
GPU1	NV8	 X 	NV8	NV8	NV8	NV8	NV8	NV8	PXB	NODE	NODE	NODE	SYS	SYS	0-31,64-95	0		N/A
GPU2	NV8	NV8	 X 	NV8	NV8	NV8	NV8	NV8	NODE	NODE	NODE	PXB	SYS	SYS	0-31,64-95	0		N/A
GPU3	NV8	NV8	NV8	 X 	NV8	NV8	NV8	NV8	NODE	NODE	NODE	PXB	SYS	SYS	0-31,64-95	0		N/A
GPU4	NV8	NV8	NV8	NV8	 X 	NV8	NV8	NV8	SYS	SYS	SYS	SYS	PXB	NODE	32-63,96-127	1		N/A
GPU5	NV8	NV8	NV8	NV8	NV8	 X 	NV8	NV8	SYS	SYS	SYS	SYS	PXB	NODE	32-63,96-127	1		N/A
GPU6	NV8	NV8	NV8	NV8	NV8	NV8	 X 	NV8	SYS	SYS	SYS	SYS	NODE	PXB	32-63,96-127	1		N/A
GPU7	NV8	NV8	NV8	NV8	NV8	NV8	NV8	 X 	SYS	SYS	SYS	SYS	NODE	PXB	32-63,96-127	1		N/A
NIC0	PXB	PXB	NODE	NODE	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	SYS	SYS
NIC1	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	 X 	PIX	NODE	SYS	SYS
NIC2	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	PIX	 X 	NODE	SYS	SYS
NIC3	NODE	NODE	PXB	PXB	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	SYS	SYS
NIC4	SYS	SYS	SYS	SYS	PXB	PXB	NODE	NODE	SYS	SYS	SYS	SYS	 X 	NODE
NIC5	SYS	SYS	SYS	SYS	NODE	NODE	PXB	PXB	SYS	SYS	SYS	SYS	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

How would you like to use vllm

I want to start distributed inference server on multi-node multi-gpu with torchrun.

However I cannot get it work.

  • On master node
VLLM_HOST_IP=master_ip \
VLLM_PORT=41818 \
VLLM_ALLOW_ENGINE_USE_RAY=0 \
CUDA_LAUNCH_BLOCKING=1 \
VLLM_LOGGING_LEVEL=DEBUG \
VLLM_TRACE_FUNCTION=1 \
NCCL_DEBUG=TRACE \
CUDA_VISIBLE_DEVICES=0,1 \
torchrun --nnodes 2 --nproc-per-node=2 --node_rank=0 \
  --master_addr=master_ip --master_port=40693 \
  -m vllm.entrypoints.openai.api_server \
  --gpu_memory_utilization 0.9 \
  --seed 9527 \
  --tokenizer Baichuan2-13B-Chat \
  --model Baichuan2-13B-Chat \
  --trust_remote_code \
  --host master_ip \
  --port master_port \
  --tensor-parallel-size 4
  • On worker node
VLLM_HOST_IP=master_ip \
VLLM_PORT=41818 \
VLLM_ALLOW_ENGINE_USE_RAY=0 \
VLLM_LOGGING_LEVEL=DEBUG \
CUDA_LAUNCH_BLOCKING=1 \
VLLM_TRACE_FUNCTION=1 \
NCCL_DEBUG=TRACE \
CUDA_VISIBLE_DEVICES=0,1 \
torchrun --nnodes 2 --nproc-per-node=2 --node_rank=1 \
  --master_addr=master_ip --master_port=40693 \
  -m vllm.entrypoints.openai.api_server \
  --gpu_memory_utilization 0.9 \
  --seed 9527 \
  --tokenizer Baichuan2-13B-Chat \
  --model Baichuan2-13B-Chat \
  --trust_remote_code \
  --host master_ip \
  --port master_port \
  --tensor-parallel-size 4

Can someone help me? Thanks a lot.

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
@ericxsun ericxsun added the usage How to use vllm label Aug 30, 2024
@youkaichao
Copy link
Member

we don't support torchrun . if you want to scale the number of vllm instances, maybe you'd be interested at https://docs.ray.io/en/latest/serve/tutorials/vllm-example.html

@ericxsun
Copy link
Author

ericxsun commented Sep 2, 2024 •
edited
Loading

https://docs.ray.io/en/latest/serve/tutorials/vllm-example.html

Thanks a lot.

As you mentioned in #3587 (comment) and #3902, could we can use torchrun in the near future?

@antoineDievDecath
Copy link

we don't support torchrun . if you want to scale the number of vllm instances, maybe you'd be interested at https://docs.ray.io/en/latest/serve/tutorials/vllm-example.html

Can this code exemple be used for llama70b ?

@youkaichao
Copy link
Member

@antoineDievDecath sure, use -tp 4 should be enough for llama 70b with H100.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
usage How to use vllm
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@ericxsun @youkaichao @antoineDievDecath