[Bug]: v0.8.2 generates incomplete sequences for Qwen2-VL-7B under specific concurrency range #15677
Description
Your current environment
The output of `python collect_env.py`
INFO 03-28 13:42:11 [__init__.py:239] Automatically detected platform cuda.
Collecting environment information...
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
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 3.31.6
Libc version: glibc-2.35
Python version: 3.12.9 (main, Feb 5 2025, 08:49:00) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.10.0-1.0.0.35-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA L20
GPU 1: NVIDIA L20
GPU 2: NVIDIA L20
GPU 3: NVIDIA L20
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
BIOS Vendor ID: Intel(R) Corporation
Model name: Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz
BIOS Model name: Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 32
Socket(s): 2
Stepping: 6
CPU max MHz: 3500.0000
CPU min MHz: 800.0000
BogoMIPS: 5200.00
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 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 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 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 3 MiB (64 instances)
L1i cache: 2 MiB (64 instances)
L2 cache: 80 MiB (64 instances)
L3 cache: 96 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-31,64-95
NUMA node1 CPU(s): 32-63,96-127
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: 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
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-cusparselt-cu12==0.6.2
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.3.0
[pip3] torch==2.6.0
[pip3] torchaudio==2.6.0
[pip3] torchvision==0.21.0
[pip3] transformers==4.50.1
[pip3] triton==3.2.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.8.2
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 NIC0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NODE SYS SYS NODE 0-31,64-95 0 N/A
GPU1 NODE X SYS SYS NODE 0-31,64-95 0 N/A
GPU2 SYS SYS X NODE SYS 32-63,96-127 1 N/A
GPU3 SYS SYS NODE X SYS 32-63,96-127 1 N/A
NIC0 NODE NODE 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_bond_0
NVIDIA_VISIBLE_DEVICES=GPU-98483900-1192-4809-4004-620b45c474f8
NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536
NCCL_VERSION=2.21.5-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_VISIBLE_GPUS_UUID=GPU-98483900-1192-4809-4004-620b45c474f8
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=12.4.1
VLLM_DO_NOT_TRACK=1
LD_LIBRARY_PATH=/home/opt/nvidia_lib
NVIDIA_VISIBLE_GPUS_SLOT=0
VLLM_USE_V1=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
- Model: Vanilla Qwen2-VL-7B-Instruct (Although the "model" field in the response below says "qwen-7b-vl", we verified that the model being used was the HuggingFace Hub version of Qwen2-VL-7B-Instruct.)
- GPU: L20 & A800
Bug Details
We constructed a load testing request set with the same prompt but around 100 different images and observed that during load testing with a range of virtual users (vu) between 24 and 44 on L20 GPU, vLLM generated incomplete sequences because eos was emitted prematurely:
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":"This"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" image"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" depicts"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" natural"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" forest"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"stop","stop_reason":null}]}
data: {"id":"chatcmpl-f5f2b9844bdd45cfad93428ece35e3a1","object":"chat.completion.chunk","created":1743141408,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1973,"total_tokens":1980,"completion_tokens":7}}
data: [DONE]
vLLM log during generation: vllm-log.txt. Notably, we didn't observe any error.
Outside of this concurrency range, generation is completely normal. Attached is the response for the same prompt and image, but at a concurrency level of 20: response-20-vu.txt
Troubleshooting
We were able to reproduce the same issue on vLLM v0.8.0 + A800 GPU, but not on v0.8.2 + A800. The concurrency range that caused the issues is also different with a higher starting threshold at 28 vu. We performed a bisection and discovered that it was 1fe0fd1 that fixed this issue for A800 but not L20. Critically, partially reverting the change on the video line in this commit will make this issue reproducible again on A800 for vLLM v0.8.2.
We also discovered that disable prefix caching will completely fix this issue.
Minimally Reproducible Example
Download the request set:
The requests has been split into two parts as it exceeds GitHub's upload limit. Extract the files with:
cat requests.a* | tar -xf -Get vLLM up and running with the model Qwen/Qwen2-VL-7B-Instruct, and then send requests with:
for i in $(seq 1 <concurrency>); do curl --location http://<vllm-endpoint> --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens & done; waitReplace <concurrency> with your desirable concurrency level. Look for abnormally low completion_tokens count in the output. Here is an example output where I set <concurrency> to 26, sent the requests and then looked for problematic output (the file output/12 in this case):
$ for i in $(seq 1 26); do curl --location http://<redacted>/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens & done; wait
[1] 68671
[2] 68674
[3] 68677
[4] 68680
[5] 68683
[6] 68686
[7] 68689
[8] 68692
[9] 68695
[10] 68698
[11] 68701
[12] 68704
[13] 68707
[14] 68710
[15] 68713
[16] 68716
[17] 68719
[18] 68722
[19] 68725
[20] 68728
[21] 68731
[22] 68734
[23] 68737
[24] 68740
[25] 68743
[26] 68746
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1990,"total_tokens":1996,"completion_tokens":6}}
data: {"id":"chatcmpl-4052cb97-2bbd-49b4-8e8d-876629c430ff","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1281,"completion_tokens":7}}
data: {"id":"chatcmpl-47986987-8ceb-467b-ac37-bf1e450b8298","object":"chat.completion.chunk","created":1743149492,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1944,"total_tokens":1950,"completion_tokens":6}}
data: {"id":"chatcmpl-333069e1-1734-40ec-9450-857589edb63f","object":"chat.completion.chunk","created":1743149492,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1380,"completion_tokens":106}}
data: {"id":"chatcmpl-238a71e6-a69e-474a-b480-b15e70dad705","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1328,"total_tokens":1439,"completion_tokens":111}}
data: {"id":"chatcmpl-1532f304-c4bb-4889-9aee-60630d07d1f2","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1418,"total_tokens":1529,"completion_tokens":111}}
data: {"id":"chatcmpl-4bfcce78-4a3f-466f-86b3-28094904aaeb","object":"chat.completion.chunk","created":1743149492,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1383,"completion_tokens":109}}
data: {"id":"chatcmpl-4bc9eab9-c883-45de-b5fe-e6ee5b24aba5","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1187,"total_tokens":1301,"completion_tokens":114}}
data: {"id":"chatcmpl-4283998d-aa4c-4de9-88df-6dc4c93161c7","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1390,"completion_tokens":116}}
data: {"id":"chatcmpl-2f5be22c-e6bc-4258-83fa-0b93d68d5fa7","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1418,"total_tokens":1536,"completion_tokens":118}}
data: {"id":"chatcmpl-445af493-2620-4ac0-ab8b-d90d6e2f56d8","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1328,"total_tokens":1452,"completion_tokens":124}}
data: {"id":"chatcmpl-07616932-b129-4ae1-99c9-d9781360b530","object":"chat.completion.chunk","created":1743149489,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1418,"total_tokens":1550,"completion_tokens":132}}
data: {"id":"chatcmpl-2f9cb268-619d-4f86-86f2-f2919ea3acf6","object":"chat.completion.chunk","created":1743149492,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1402,"completion_tokens":128}}
data: {"id":"chatcmpl-19663b74-9ff9-4ac4-ab50-60f9f9466a70","object":"chat.completion.chunk","created":1743149489,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1184,"total_tokens":1328,"completion_tokens":144}}
data: {"id":"chatcmpl-0f645782-d0b9-4300-9ec2-2411651aaa07","object":"chat.completion.chunk","created":1743149492,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1461,"completion_tokens":187}}
data: {"id":"chatcmpl-2a902a30-4c38-47d9-afd5-57d46101fd58","object":"chat.completion.chunk","created":1743149489,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1479,"completion_tokens":205}}
data: {"id":"chatcmpl-075d5d90-a6da-43fb-8b2e-274857604f77","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1328,"total_tokens":1538,"completion_tokens":210}}
data: {"id":"chatcmpl-1cd7ff1d-15a7-4469-9f22-073a7edc0e74","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1328,"total_tokens":1544,"completion_tokens":216}}
data: {"id":"chatcmpl-37c6d0c0-9e47-45ce-b335-99cbc135c12f","object":"chat.completion.chunk","created":1743149488,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1505,"completion_tokens":231}}
data: {"id":"chatcmpl-1ba7b686-28e3-4849-b564-ca79a34b70d3","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1944,"total_tokens":2166,"completion_tokens":222}}
data: {"id":"chatcmpl-295384ba-84c2-4bb1-b753-77b2d4d9ffd6","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1274,"total_tokens":1497,"completion_tokens":223}}
data: {"id":"chatcmpl-207fd97c-955d-47ac-8a44-aef73443fa3f","object":"chat.completion.chunk","created":1743149489,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1058,"total_tokens":1312,"completion_tokens":254}}
data: {"id":"chatcmpl-04aeb337-77fa-4f0f-a309-755025308d25","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1150,"total_tokens":1410,"completion_tokens":260}}
data: {"id":"chatcmpl-015201a8-b879-40c1-be49-3ac4e18a48b6","object":"chat.completion.chunk","created":1743149489,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1328,"total_tokens":1667,"completion_tokens":339}}
[1] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[2] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[3] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[4] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[5] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[7] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[8] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[9] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[10] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[11] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[12] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[13] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[14] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[15] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[17] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[18] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[19] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[20] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[21] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[22] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[23] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[24] Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[25]- Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[26]+ Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
data: {"id":"chatcmpl-2b4b269a-ba1a-4547-8322-01e75d1da257","object":"chat.completion.chunk","created":1743149492,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1256,"total_tokens":1609,"completion_tokens":353}}
data: {"id":"chatcmpl-142f7335-7fb4-4a4c-98d7-61207e4d8e1b","object":"chat.completion.chunk","created":1743149490,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1364,"total_tokens":1799,"completion_tokens":435}}
[6]- Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
[16]+ Done curl --location http://10.56.250.170:8081/v1/chat/completions --header 'Content-Type: application/json; encoding=utf-8' --data-binary "@requests/$i.json" -s | tee output/$i | grep completion_tokens
$ grep -r chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67 output
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":"This"},"logprobs":null,"finish_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" image"},"logprobs":null,"finish_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" depicts"},"logprobs":null,"finish_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" an"},"logprobs":null,"finish_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"stop","stop_reason":null}]}
output/12:data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1990,"total_tokens":1996,"completion_tokens":6}}
$ cat output/12
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":"This"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" image"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" depicts"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" an"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"stop","stop_reason":null}]}
data: {"id":"chatcmpl-218f3455-ef1f-4ba6-9ea1-d6bd0acece67","object":"chat.completion.chunk","created":1743149491,"model":"qwen-7b-vl/","choices":[],"usage":{"prompt_tokens":1990,"total_tokens":1996,"completion_tokens":6}}
data: [DONE]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.