[Bug]: Improve Error Messaging for Unsupported Tasks in vLLM (e.g., embedding with Llama Models) #10794
Open
1 task done
Assignees
Labels
bug
Something isn't working
Comments
|
Can you try pulling the latest code and check that if the issue still occurs? Please note that #10769 now enables any model to be used as an embedding model if you pass |
Hi @DarkLight1337 I try to use an opt model for embedding task: And generate embeddings like this: It returns a ValueError, which asks for Maybe I just using this new feature in a wrong way... Could you help me see if there any problems here |
|
I'm able to run this code: from vllm import LLM
# Sample prompts.
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create an LLM.
model = LLM(model="facebook/opt-125m", task="embedding")
# Generate embedding. The output is a list of PoolingRequestOutputs.
outputs = model.encode(prompts)
# Print the outputs.
for output in outputs:
print(output.outputs.embedding) # list of 4096 floats |
|
I have a hunch that the bug is hiding in the json serialization. When poking around, I believe I saw a pydantic error flying by. Will try with the latest version tomorrow after work. |
|
@DarkLight1337 Thanks, I run your code successfully. I found that maybe the bug is due to the config of So I manually add truncation outside my code, limit the max token length to 512. Now it can run successfully. In vllm/outputs.py: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Your current environment
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Debian GNU/Linux trixie/sid (x86_64)
GCC version: (GCC) 12.3.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.40
Python version: 3.11.9 (main, Apr 10 2024, 13:16:36) [GCC 13.2.0] (64-bit runtime)
Python platform: Linux-6.8.12-amd64-x86_64-with-glibc2.40
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A40
GPU 1: NVIDIA A40
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
Address sizes: 48 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 7443P 24-Core Processor
CPU family: 25
Model: 1
Thread(s) per core: 1
Core(s) per socket: 24
Socket(s): 1
Stepping: 1
Frequency boost: enabled
CPU(s) scaling MHz: 51%
CPU max MHz: 4035.6440
CPU min MHz: 1500.0000
BogoMIPS: 5699.82
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 pcid 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 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni
xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists paus
efilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca debug_swap
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 (4 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: Not affected
Vulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode
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; IBRS_FW; 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] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.46.3
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.4.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 NIC0 NIC1 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PIX SYS SYS 0-23 0 N/A
GPU1 PIX X SYS SYS 0-23 0 N/A
NIC0 SYS SYS X PIX
NIC1 SYS 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
LD_LIBRARY_PATH=/home/ben/tmp/lib/python3.11/site-packages/cv2/../../lib64:
CUDA_MODULE_LOADING=LAZY
Model Input Dumps
No response
🐛 Describe the bug
When attempting to use the embedding task with a model that does not support it (e.g.,
meta-llama/Llama-3.2-3B-Instruct), the server responds with a 400 Bad Request error and a generic error message. The response does not provide any actionable information to indicate that the issue arises because the model does not support the embedding task.This leads to unnecessary debugging efforts, as the error message does not make it clear that the problem is related to task compatibility.
The vllm version: 0.6.4.post1
Steps to Reproduce
Start the vLLM server with the following command:
Send an embedding request:
Observe the response:
Expected Behavior
The server should return a more descriptive error message explaining the issue, such as:
Actual Behavior
The server returns a generic 400 Bad Request error with no clear indication of the problem. This makes it unclear whether the issue is due to:
I confirm that this issue does not manifest when using a model that supports embeddings, such as
sentence-transformers/all-MiniLM-L6-v2Before submitting a new issue...
The text was updated successfully, but these errors were encountered: