vllm - ✅(Solved) Fix [Bug]: Streaming chat completion drops partial content when stop string interrupts auto tool parsing [1 pull requests, 1 participants]

vllm2026-05-10 06:50:40

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#42210•Fetched 2026-05-11 03:13:48

View on GitHub

Comments

Participants

Timeline

Reactions

Author

TheDuyIT

Participants

TheDuyIT

Timeline (top)

cross-referenced ×1labeled ×1

Root Cause

There is also a related finish-reason issue: when the stop was caused by a user-requested stop string, the final streaming response should preserve finish_reason: "stop" instead of treating the partial parser state as a completed tool call.

Fix Action

Fix / Workaround

============================== CPU Info

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): 256 On-line CPU(s) list: 0-255 Vendor ID: AuthenticAMD Model name: AMD EPYC 7742 64-Core Processor CPU family: 23 Model: 49 Thread(s) per core: 2 Core(s) per socket: 64 Socket(s): 2 Stepping: 0 Frequency boost: enabled CPU(s) scaling MHz: 50% CPU max MHz: 3414.5500 CPU min MHz: 1500.0000 BogoMIPS: 4500.07 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 xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic 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 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd 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: 4 MiB (128 instances) L1i cache: 4 MiB (128 instances) L2 cache: 64 MiB (128 instances) L3 cache: 512 MiB (32 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-63,128-191 NUMA node1 CPU(s): 64-127,192-255 Vulnerability Gather data sampling: Not affected Vulnerability Ghostwrite: Not affected Vulnerability Indirect target selection: 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 Old microcode: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection Vulnerability Spec rstack overflow: Mitigation; Safe RET 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 always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

PR fix notes

PR #42213: [Bugfix] Fix streaming stop handling during tool parsing

Repository: vllm-project/vllm
Author: TheDuyIT
State: open | merged: False
Link: https://github.com/vllm-project/vllm/pull/42213

Description (problem / solution / changelog)

Purpose

Fixes #42210

When a requested stop string interrupts streaming auto tool parsing before any tool-call delta is emitted, vLLM can drop the partial generated content and report the response as a tool call. This PR preserves finish_reason="stop" for request-provided stop reasons and flushes the parser-buffered partial text as assistant content so streaming matches non-streaming behavior.

Test Plan

Run the targeted streaming chat-completion regression tests:

.venv/bin/python -m pytest \
  tests/entrypoints/openai/chat_completion/test_serving_chat.py::test_streaming_n_gt1_independent_tool_parsers \
  tests/entrypoints/openai/chat_completion/test_serving_chat.py::test_streaming_tool_parser_preserves_requested_stop_reason \
  -q

Manual API validation:

vllm serve meta-llama/Llama-3.1-8B-Instruct \
  --max-model-len 8192 \
  --served-model-name base_model \
  --enable-auto-tool-choice \
  --tool-call-parser llama3_json

curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "base_model",
    "stream": true,
    "stop": ["a"],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in San Francisco?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string"
              }
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

Test Result

Targeted pytest:

2 passed

Manual API validation:

The final streaming chunk returned finish_reason="stop", stop_reason="a", and
included the partial generated content in delta.content.

data: ... "delta":{"content":"{\"n"},"finish_reason":"stop","stop_reason":"a" ...
data: [DONE]

AI assistance

AI assistance (Codex GPT-5.5) was used to help prepare this patch. The human submitter reviewed the changed lines and ran the tests above.

<details> <summary> Essential Elements of an Effective PR Description Checklist </summary>

The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
The test plan, such as providing test command.
The test results, such as pasting the results comparison before and after, or e2e results
(Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

</details>

Changed files

tests/entrypoints/openai/chat_completion/test_serving_chat.py (modified, +259/-0)
vllm/entrypoints/openai/chat_completion/serving.py (modified, +64/-1)

Code Example

Collecting environment information...
uv is set
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.4 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, May  4 2026, 21:09:48) [Clang 22.1.3 ] (64-bit runtime)
Python platform              : Linux-6.17.0-19-generic-x86_64-with-glibc2.39
    
==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : Could not collect
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : 
GPU 0: NVIDIA A10
GPU 1: NVIDIA A10
GPU 2: NVIDIA A10
GPU 3: NVIDIA A10
GPU 4: NVIDIA A10
GPU 5: NVIDIA A10
GPU 6: NVIDIA A10
GPU 7: NVIDIA A10

Nvidia driver version        : 595.71.05
cuDNN version                : Could not collect
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:                           43 bits physical, 48 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 7742 64-Core Processor
CPU family:                              23
Model:                                   49
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                0
Frequency boost:                         enabled
CPU(s) scaling MHz:                      50%
CPU max MHz:                             3414.5500
CPU min MHz:                             1500.0000
BogoMIPS:                                4500.07
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 xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic 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 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd 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:                               4 MiB (128 instances)
L1i cache:                               4 MiB (128 instances)
L2 cache:                                64 MiB (128 instances)
L3 cache:                                512 MiB (32 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-63,128-191
NUMA node1 CPU(s):                       64-127,192-255
Vulnerability Gather data sampling:      Not affected
Vulnerability Ghostwrite:                Not affected
Vulnerability Indirect target selection: 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 Old microcode:             Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow:      Mitigation; Safe RET
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 always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.8.post1
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.2.6
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-cutlass-dsl==4.5.0
[pip3] nvidia-cutlass-dsl-libs-base==4.5.0
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] open-clip-torch==2.32.0
[pip3] pyzmq==27.1.0
[pip3] segmentation-models-pytorch==0.5.0
[pip3] sentence-transformers==5.2.0
[pip3] torch==2.11.0+cu130
[pip3] torch-c-dlpack-ext==0.1.5
[pip3] torchaudio==2.11.0+cu130
[pip3] torchvision==0.26.0+cu130
[pip3] transformers==5.5.3
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.6.0
[pip3] tritonclient==2.64.0
[pip3] vector-quantize-pytorch==1.21.2
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.20.2rc1.dev132+g445d74743 (git sha: 445d74743)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU1    NODE     X      NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU2    NODE    NODE     X      NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU3    NODE    NODE    NODE     X      SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU4    SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    NODE    NODE    64-127,192-255  1               N/A
GPU5    SYS     SYS     SYS     SYS     NODE     X      NODE    NODE    NODE    NODE    64-127,192-255  1               N/A
GPU6    SYS     SYS     SYS     SYS     NODE    NODE     X      NODE    PHB     PHB     64-127,192-255  1               N/A
GPU7    SYS     SYS     SYS     SYS     NODE    NODE    NODE     X      NODE    NODE    64-127,192-255  1               N/A
NIC0    SYS     SYS     SYS     SYS     NODE    NODE    PHB     NODE     X      PIX
NIC1    SYS     SYS     SYS     SYS     NODE    NODE    PHB     NODE    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

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_local-dtnguyen

---

vllm serve meta-llama/Llama-3.1-8B-Instruct \
  --max-model-len 8192 \
  --served-model-name base_model \
  --enable-auto-tool-choice \
  --tool-call-parser llama3_json

---

curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "base_model",
    "stream": true,
    "stop": ["a"],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in San Francisco?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string"
              }
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

---

data: ... "delta":{"role":"assistant","content":""} ...
data: ... "delta":{"content":""} ...
data: ... "delta":{},"finish_reason":"tool_calls","stop_reason":"a" ...
data: [DONE]

---

curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "base_model",
    "stream": false,
    "stop": ["a"],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in San Francisco?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string"
              }
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

---

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "{\"n",
        "tool_calls": []
      },
      "finish_reason": "stop",
      "stop_reason": "a"
    }
  ]
}

---

data: ... "delta":{"content":"{\"n"},"finish_reason":"stop","stop_reason":"a" ...
data: [DONE]

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

Collecting environment information...
uv is set
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.4 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version                : Could not collect
CMake version                : Could not collect
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A
XPU used to build PyTorch    : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, May  4 2026, 21:09:48) [Clang 22.1.3 ] (64-bit runtime)
Python platform              : Linux-6.17.0-19-generic-x86_64-with-glibc2.39
    
==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : Could not collect
CUDA_MODULE_LOADING set to   : 
GPU models and configuration : 
GPU 0: NVIDIA A10
GPU 1: NVIDIA A10
GPU 2: NVIDIA A10
GPU 3: NVIDIA A10
GPU 4: NVIDIA A10
GPU 5: NVIDIA A10
GPU 6: NVIDIA A10
GPU 7: NVIDIA A10

Nvidia driver version        : 595.71.05
cuDNN version                : Could not collect
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:                           43 bits physical, 48 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  256
On-line CPU(s) list:                     0-255
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 7742 64-Core Processor
CPU family:                              23
Model:                                   49
Thread(s) per core:                      2
Core(s) per socket:                      64
Socket(s):                               2
Stepping:                                0
Frequency boost:                         enabled
CPU(s) scaling MHz:                      50%
CPU max MHz:                             3414.5500
CPU min MHz:                             1500.0000
BogoMIPS:                                4500.07
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 xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic 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 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd 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:                               4 MiB (128 instances)
L1i cache:                               4 MiB (128 instances)
L2 cache:                                64 MiB (128 instances)
L3 cache:                                512 MiB (32 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-63,128-191
NUMA node1 CPU(s):                       64-127,192-255
Vulnerability Gather data sampling:      Not affected
Vulnerability Ghostwrite:                Not affected
Vulnerability Indirect target selection: 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 Old microcode:             Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow:      Mitigation; Safe RET
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 always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.8.post1
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.2.6
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-cutlass-dsl==4.5.0
[pip3] nvidia-cutlass-dsl-libs-base==4.5.0
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] open-clip-torch==2.32.0
[pip3] pyzmq==27.1.0
[pip3] segmentation-models-pytorch==0.5.0
[pip3] sentence-transformers==5.2.0
[pip3] torch==2.11.0+cu130
[pip3] torch-c-dlpack-ext==0.1.5
[pip3] torchaudio==2.11.0+cu130
[pip3] torchvision==0.26.0+cu130
[pip3] transformers==5.5.3
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.6.0
[pip3] tritonclient==2.64.0
[pip3] vector-quantize-pytorch==1.21.2
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.20.2rc1.dev132+g445d74743 (git sha: 445d74743)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU1    NODE     X      NODE    NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU2    NODE    NODE     X      NODE    SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU3    NODE    NODE    NODE     X      SYS     SYS     SYS     SYS     SYS     SYS     0-63,128-191    0               N/A
GPU4    SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    NODE    NODE    64-127,192-255  1               N/A
GPU5    SYS     SYS     SYS     SYS     NODE     X      NODE    NODE    NODE    NODE    64-127,192-255  1               N/A
GPU6    SYS     SYS     SYS     SYS     NODE    NODE     X      NODE    PHB     PHB     64-127,192-255  1               N/A
GPU7    SYS     SYS     SYS     SYS     NODE    NODE    NODE     X      NODE    NODE    64-127,192-255  1               N/A
NIC0    SYS     SYS     SYS     SYS     NODE    NODE    PHB     NODE     X      PIX
NIC1    SYS     SYS     SYS     SYS     NODE    NODE    PHB     NODE    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

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_local-dtnguyen

</details>

🐛 Describe the bug

Summary

When using the OpenAI-compatible chat completions API with streaming, auto tool choice, and the llama3_json tool parser, a user-provided stop string can interrupt generation while the model has only produced partial tool-call-looking JSON.

In this case, non-streaming returns the partial generated text as assistant content, but streaming drops that partial text and sends an empty final delta.

This makes streaming and non-streaming behavior inconsistent for the same request.

Reproduction

Start the server:

vllm serve meta-llama/Llama-3.1-8B-Instruct \
  --max-model-len 8192 \
  --served-model-name base_model \
  --enable-auto-tool-choice \
  --tool-call-parser llama3_json

Send a streaming request with a stop string:

curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "base_model",
    "stream": true,
    "stop": ["a"],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in San Francisco?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string"
              }
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

Actual streaming output, minimized:

data: ... "delta":{"role":"assistant","content":""} ...
data: ... "delta":{"content":""} ...
data: ... "delta":{},"finish_reason":"tool_calls","stop_reason":"a" ...
data: [DONE]

That is unexpected because the stop reason came from the request's stop string.

Compare with the same request using non-streaming:

curl -s http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "base_model",
    "stream": false,
    "stop": ["a"],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in San Francisco?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string"
              }
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

Non-streaming returns the partial generated content:

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "{\"n",
        "tool_calls": []
      },
      "finish_reason": "stop",
      "stop_reason": "a"
    }
  ]
}

Expected behavior

Streaming should preserve the same partial content that non-streaming returns, while still reporting the user-requested stop:

data: ... "delta":{"content":"{\"n"},"finish_reason":"stop","stop_reason":"a" ...
data: [DONE]

The partial content should not be dropped just because the streaming tool parser had buffered state while deciding whether the output was a tool call.

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.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #generation error #database connection #vector store #environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

vllm - ✅(Solved) Fix [Bug]: Streaming chat completion drops partial content when stop string interrupts auto tool parsing [1 pull requests, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Root Cause

Fix Action

Fix / Workaround

============================== CPU Info

PR fix notes

PR #42213: [Bugfix] Fix streaming stop handling during tool parsing

Description (problem / solution / changelog)

Purpose

Test Plan

Test Result

AI assistance

Changed files

Code Example

Your current environment

🐛 Describe the bug

Summary

Reproduction

Expected behavior

Before submitting a new issue...

Still need to ship something?

TRENDING

vllm - ✅(Solved) Fix [Bug]: Streaming chat completion drops partial content when stop string interrupts auto tool parsing [1 pull requests, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Root Cause

Fix Action

Fix / Workaround

============================== CPU Info

PR fix notes

PR #42213: [Bugfix] Fix streaming stop handling during tool parsing

Description (problem / solution / changelog)

Purpose

Test Plan

Test Result

AI assistance

Changed files

Code Example

Your current environment

🐛 Describe the bug

Summary

Reproduction

Expected behavior

Before submitting a new issue...

Still need to ship something?

RELATED_DISCOVERY

TRENDING