vllm: [Bug]: PaliGemma serving
Your current environment
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 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35
Python version: 3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.1.0-21-amd64-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A800 80GB PCIe
Nvidia driver version: 525.147.05
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: 43 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 24
On-line CPU(s) list: 0-23
Vendor ID: AuthenticAMD
Model name: AMD EPYC 7352 24-Core Processor
CPU family: 23
Model: 49
Thread(s) per core: 1
Core(s) per socket: 24
Socket(s): 1
Stepping: 0
Frequency boost: enabled
CPU max MHz: 2300.0000
CPU min MHz: 1500.0000
BogoMIPS: 4600.10
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 mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es
Virtualization: AMD-V
L1d cache: 768 KiB (24 instances)
L1i cache: 768 KiB (24 instances)
L2 cache: 12 MiB (24 instances)
L3 cache: 128 MiB (8 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-23
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 Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled
Vulnerability Spec rstack overflow: Mitigation; SMT disabled
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] lion-pytorch==0.1.4
[pip3] numpy==1.26.4
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] onnx==1.16.0
[pip3] onnx-graphsurgeon==0.5.2
[pip3] onnxruntime==1.16.3
[pip3] onnxruntime-gpu==1.17.1
[pip3] open-clip-torch==2.24.0
[pip3] pytorch-lightning==2.2.4
[pip3] torch==2.3.1
[pip3] torchaudio==2.3.1
[pip3] torchdata==0.7.1
[pip3] torchmetrics==1.3.2
[pip3] torchvision==0.18.1
[pip3] transformers==4.42.4
[pip3] triton==2.3.1
[pip3] tritonclient==2.45.0
[conda] lion-pytorch 0.1.4 pypi_0 pypi
[conda] numpy 1.26.4 py311h24aa872_0
[conda] numpy-base 1.26.4 py311hbfb1bba_0
[conda] nvidia-nccl-cu12 2.20.5 pypi_0 pypi
[conda] open-clip-torch 2.24.0 pypi_0 pypi
[conda] pytorch-lightning 2.2.4 pypi_0 pypi
[conda] torch 2.3.1 pypi_0 pypi
[conda] torchaudio 2.3.1 pypi_0 pypi
[conda] torchdata 0.7.1 pypi_0 pypi
[conda] torchmetrics 1.3.2 pypi_0 pypi
[conda] torchvision 0.18.1 pypi_0 pypi
[conda] transformers 4.42.4 pypi_0 pypi
[conda] triton 2.3.1 pypi_0 pypi
[conda] tritonclient 2.45.0 pypi_0 pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.2
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 NIC0 NIC1 CPU Affinity NUMA Affinity
GPU0 X SYS SYS 0-23 N/A
NIC0 SYS X PIX
NIC1 SYS PIX 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
🐛 Describe the bug
I run the following docker container
docker run --runtime nvidia --gpus all -v ~/.cache/huggingface:/root/.cache/huggingface -p 8000:8000 --env "HUGGING_FACE_HUB_TOKEN=[MY_TOKEN_HERE]" vllm/vllm-openai --model google/paligemma-3b-mix-224
And after it is up & running, I execute the following python code
import base64
import requests
from openai import OpenAI
# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
# defaults to os.environ.get("OPENAI_API_KEY")
api_key=openai_api_key,
base_url=openai_api_base,
)
models = client.models.list()
model = models.data[0].id
image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
# Use base64 encoded image in the payload
def encode_image_base64_from_url(image_url: str) -> str:
"""Encode an image retrieved from a remote url to base64 format."""
with requests.get(image_url) as response:
response.raise_for_status()
return base64.b64encode(response.content).decode('utf-8')
image_base64 = encode_image_base64_from_url(image_url=image_url)
chat_completion_from_base64 = client.chat.completions.create(
messages=[{
"role":
"user",
"content": [
{
"type": "text",
"text": "USER: <image>\nWhat is the content of this image?\nASSISTANT:",
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{image_base64}"
},
},
],
}],
model=model,
)
result = chat_completion_from_base64.choices[0].message.content
print(f"Chat completion output:{result}")
This results in the following ooutput:
Chat completion output:<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
<|im_end>
Please help.
About this issue
- Original URL
- State: closed
- Created 2 years ago
- Comments: 15 (6 by maintainers)
Hey @arseniybelkov I just want to let you know this is still on my list of TODO but I simply had limited bandwidth with other priorities. Sorry for the inconvenience!
@ywang96 Here is the code and image