[Bug]:qwen2_5vl: Internal Server Error when processing short video and vllm has been installed 0.9.0 #20313
Description
Your current environment
The output of python collect_env.py
NFO 07-01 10:11:23 [__init__.py:243] Automatically detected platform cuda.
Collecting environment information...
==============================
System Info
==============================
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 3.30.2
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.7.0+cu126
Is debug build : False
CUDA used to build PyTorch : 12.6
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0] (64-bit runtime)
Python platform : Linux-5.15.0-88-generic-x86_64-with-glibc2.35
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.6.20
CUDA_MODULE_LOADING set to : LAZY
GPU models and configuration : GPU 0: NVIDIA H100 80GB HBM3
Nvidia driver version : 535.154.05
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.3.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.3.0
HIP runtime version : N/A
MIOpen runtime version : N/A
Is XNNPACK available : True
==============================
CPU Info
==============================
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): 64
On-line CPU(s) list: 0-63
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8462Y+
CPU family: 6
Model: 143
Thread(s) per core: 1
Core(s) per socket: 32
Socket(s): 2
Stepping: 8
Frequency boost: enabled
CPU max MHz: 2801.0000
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 ds_cpl 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 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 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
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
NUMA node1 CPU(s): 32-63
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] mypy-extensions==1.0.0
[pip3] numpy==1.25.1
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cudnn-frontend==1.5.2
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-cufile-cu12==1.11.1.6
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-dali-cuda120==1.40.0
[pip3] nvidia-modelopt==0.15.0
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvimgcodec-cu12==0.3.0.5
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] nvidia-pyindex==1.0.9
[pip3] onnx==1.16.0
[pip3] optree==0.12.1
[pip3] pynvml==11.4.1
[pip3] pytorch-triton==3.0.0+dedb7bdf3
[pip3] pyzmq==26.1.0
[pip3] torch==2.7.0
[pip3] torch_tensorrt==2.7.0
[pip3] torchaudio==2.7.0
[pip3] torchvision==0.22.0
[pip3] transformers==4.52.3
[pip3] triton==3.3.0
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
Neuron SDK Version : N/A
vLLM Version : 0.9.0
vLLM Build Flags:
CUDA Archs: 5.2 6.0 6.1 7.0 7.2 7.5 8.0 8.6 8.7 9.0+PTX; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X SYS PIX SYS SYS SYS SYS SYS SYS SYS 0-31 0 N/A
NIC0 SYS X SYS SYS SYS SYS SYS SYS SYS SYS
NIC1 PIX SYS X SYS SYS SYS SYS SYS SYS SYS
NIC2 SYS SYS SYS X SYS SYS SYS SYS SYS SYS
NIC3 SYS SYS SYS SYS X SYS SYS SYS SYS SYS
NIC4 SYS SYS SYS SYS SYS X SYS SYS SYS SYS
NIC5 SYS SYS SYS SYS SYS SYS X SYS SYS SYS
NIC6 SYS SYS SYS SYS SYS SYS SYS X SYS SYS
NIC7 SYS SYS SYS SYS SYS SYS SYS SYS X SYS
NIC8 SYS SYS SYS SYS SYS SYS SYS SYS SYS 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
==============================
Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-79076501-df9e-473d-db0e-8bd7df0484e1
CUBLAS_VERSION=12.6.0.22
NVIDIA_REQUIRE_CUDA=cuda>=9.0
CUDA_CACHE_DISABLE=1
TORCH_CUDA_ARCH_LIST=5.2 6.0 6.1 7.0 7.2 7.5 8.0 8.6 8.7 9.0+PTX
NCCL_VERSION=2.22.3
NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
NVIDIA_PRODUCT_NAME=PyTorch
CUDA_VERSION=12.6.0.022
PYTORCH_VERSION=2.5.0a0+872d972
PYTORCH_BUILD_NUMBER=0
CUDNN_FRONTEND_VERSION=1.5.2
CUDNN_VERSION=9.3.0.75
PYTORCH_HOME=/opt/pytorch/pytorch
LD_LIBRARY_PATH=/usr/local/cuda/compat/lib.real:/usr/local/lib/python3.10/dist-packages/torch/lib:/usr/local/lib/python3.10/dist-packages/torch_tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
NVIDIA_BUILD_ID=107063150
CUDA_DRIVER_VERSION=560.35.03
PYTORCH_BUILD_VERSION=2.5.0a0+872d972
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
CUDA_MODULE_LOADING=LAZY
NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
NVIDIA_PYTORCH_VERSION=24.08
TORCH_ALLOW_TF32_CUBLAS_OVERRIDE=1
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
🐛 Describe the bug
- [Bug]: Internal Server Error when processing short video #19477 had mentioned this bug, and I have installed vllm==0.9.0.
-with the newest function load_bytes of /vllm/multimodal/video.py
@classmethod
def load_bytes(cls, data: bytes, num_frames: int = -1) -> npt.NDArray:
import cv2
backend = cls().get_cv2_video_api()
cap = cv2.VideoCapture(BytesIO(data), backend, [])
if not cap.isOpened():
raise ValueError("Could not open video stream")
total_frames_num = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
full_read = num_frames == -1 or total_frames_num < num_frames
if full_read:
num_frames = total_frames_num
frame_idx = list(range(0, num_frames))
else:
uniform_sampled_frames = np.linspace(0,
total_frames_num - 1,
num_frames,
dtype=int)
frame_idx = uniform_sampled_frames.tolist()
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
frames = np.empty((len(frame_idx), height, width, 3), dtype=np.uint8)
i = 0
for idx in range(total_frames_num):
ok = cap.grab() # next img
if not ok:
break
if idx in frame_idx: # only decompress needed
ret, frame = cap.retrieve()
if ret:
frames[i] = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
i += 1
# we expect all frames loaded
assert i == num_frames, (f"Expected reading {num_frames} frames, "
f"but only loaded {i} frames from video.")
return frames
- However, I still got the error when inferencing with short videos (num_frames=17, <32)
Server code
vllm serve /Qwen2.5-VL-7B-Instruct --port 5002 --max-model-len 65536 --limit-mm-per-prompt "image=64,videos=1" --tensor-parallel-size 1 --allowed-local-media-path /
Server log
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
result = await app( # type: ignore[func-returns-value]
File "/usr/local/lib/python3.10/dist-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
return await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/fastapi/applications.py", line 1054, in __call__
await super().__call__(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/applications.py", line 112, in __call__
await self.middleware_stack(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/errors.py", line 187, in __call__
raise exc
File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/errors.py", line 165, in __call__
await self.app(scope, receive, _send)
File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/cors.py", line 85, in __call__
await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/prometheus_fastapi_instrumentator/middleware.py", line 177, in __call__
raise exc
File "/usr/local/lib/python3.10/dist-packages/prometheus_fastapi_instrumentator/middleware.py", line 175, in __call__
await self.app(scope, receive, send_wrapper)
File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/exceptions.py", line 62, in __call__
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/_exception_handler.py", line 53, in wrapped_app
raise exc
File "/usr/local/lib/python3.10/dist-packages/starlette/_exception_handler.py", line 42, in wrapped_app
await app(scope, receive, sender)
File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 714, in __call__
await self.middleware_stack(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 734, in app
await route.handle(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 288, in handle
await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 76, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File "/usr/local/lib/python3.10/dist-packages/starlette/_exception_handler.py", line 53, in wrapped_app
raise exc
File "/usr/local/lib/python3.10/dist-packages/starlette/_exception_handler.py", line 42, in wrapped_app
await app(scope, receive, sender)
File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 73, in app
response = await f(request)
File "/usr/local/lib/python3.10/dist-packages/fastapi/routing.py", line 301, in app
raw_response = await run_endpoint_function(
File "/usr/local/lib/python3.10/dist-packages/fastapi/routing.py", line 212, in run_endpoint_function
return await dependant.call(**values)
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/utils.py", line 71, in wrapper
return handler_task.result()
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/utils.py", line 93, in wrapper
return await func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/api_server.py", line 559, in create_chat_completion
generator = await handler.create_chat_completion(request, raw_request)
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/serving_chat.py", line 182, in create_chat_completion
) = await self._preprocess_chat(
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/openai/serving_engine.py", line 817, in _preprocess_chat
mm_data = await mm_data_future
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/chat_utils.py", line 647, in all_mm_data
items_by_modality = {
File "/usr/local/lib/python3.10/dist-packages/vllm/entrypoints/chat_utils.py", line 648, in <dictcomp>
modality: await asyncio.gather(*items)
File "/usr/local/lib/python3.10/dist-packages/vllm/multimodal/utils.py", line 243, in fetch_video_async
return await self.load_from_url_async(
File "/usr/local/lib/python3.10/dist-packages/vllm/multimodal/utils.py", line 136, in load_from_url_async
return self._load_file_url(url_spec, media_io)
File "/usr/local/lib/python3.10/dist-packages/vllm/multimodal/utils.py", line 91, in _load_file_url
return media_io.load_file(filepath)
File "/usr/local/lib/python3.10/dist-packages/vllm/multimodal/video.py", line 177, in load_file
return self.load_bytes(data)
File "/usr/local/lib/python3.10/dist-packages/vllm/multimodal/video.py", line 157, in load_bytes
return self.video_loader.load_bytes(data, self.num_frames)
File "/usr/local/lib/python3.10/dist-packages/vllm/multimodal/video.py", line 136, in load_bytes
assert i == num_frames, (f"Expected reading {num_frames} frames, "
AssertionError: Expected reading 32 frames, but only loaded 17 frames from video.
WARNING 07-01 09:52:23 [protocol.py:57] The following fields were present in the request but ignored: {'do_sample'}
INFO: 10.178.76.128:20037 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error
WARNING 07-01 09:52:24 [protocol.py:57] The following fields were present in the request but ignored: {'do_sample'}```
### Before submitting a new issue...
- [x] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the [documentation page](https://docs.vllm.ai/en/latest/), which can answer lots of frequently asked questions.