vllm - ✅(Solved) Fix [Bug]: GLM5 on B300 generates garbage output [2 pull requests, 6 comments, 3 participants]

vllm2026-04-07 11:45:07

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#39179•Fetched 2026-04-08 03:01:35

View on GitHub

Comments

Participants

Timeline

Reactions

Author

Participants

Timeline (top)

commented ×6cross-referenced ×1labeled ×1mentioned ×1

Fix Action

Fix / Workaround

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

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 224 On-line CPU(s) list: 0-223 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) 6767P CPU family: 6 Model: 173 Thread(s) per core: 1 Core(s) per socket: 112 Socket(s): 2 Stepping: 1 BogoMIPS: 4800.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq dtes64 vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities Virtualization: VT-x Hypervisor vendor: KVM Virtualization type: full L1d cache: 7 MiB (224 instances) L1i cache: 7 MiB (224 instances) L2 cache: 896 MiB (224 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-111 NUMA node1 CPU(s): 112-223 Vulnerability Gather data sampling: Not affected Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Unknown: No mitigations Vulnerability Reg file data sampling: 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 / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Mitigation; TSX disabled Vulnerability Vmscape: Not affected

PR fix notes

PR #38989: [Bug] Fix routing bias dtype for trtllm per-block fp8 moe

Repository: vllm-project/vllm
Author: wzhao18
State: closed | merged: True
Link: https://github.com/vllm-project/vllm/pull/38989

Description (problem / solution / changelog)

Purpose

Fix [Bug]: Deepseek R1 produces incorrect output FIX https://github.com/vllm-project/vllm/issues/39179 Flashinfer v0.6.7 requires bf16 routing bias dtype for trtllm MoE. We have done this in https://github.com/vllm-project/vllm/pull/38423 for nvfp4 and fp8 per-tensor, but haven't done for fp8 per-block.

Test Plan

Test Result

main:

vllm serve deepseek-ai/DeepSeek-R1 --trust-remote-code --tensor-parallel-size 8

|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.0197|±  |0.0038|
|     |       |strict-match    |     5|exact_match|↑  |0.0000|±  |0.0000|

branch:

|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.9598|±  |0.0054|
|     |       |strict-match    |     5|exact_match|↑  |0.9591|±  |0.0055|

<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.
(Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

</details>

Changed files

vllm/model_executor/layers/fused_moe/experts/trtllm_fp8_moe.py (modified, +5/-0)

Code Example

Collecting environment information...
uv is set
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Clang version                : Could not collect
CMake version                : version 4.3.0
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar 20 2026, 00:33:26) [Clang 22.1.1 ] (64-bit runtime)
Python platform              : Linux-5.15.0-171-generic-x86_64-with-glibc2.35

==============================
       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 B300 SXM6 AC
GPU 1: NVIDIA B300 SXM6 AC
GPU 2: NVIDIA B300 SXM6 AC
GPU 3: NVIDIA B300 SXM6 AC
GPU 4: NVIDIA B300 SXM6 AC
GPU 5: NVIDIA B300 SXM6 AC
GPU 6: NVIDIA B300 SXM6 AC
GPU 7: NVIDIA B300 SXM6 AC

Nvidia driver version        : 590.48.01
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:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  224
On-line CPU(s) list:                     0-223
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) 6767P
CPU family:                              6
Model:                                   173
Thread(s) per core:                      1
Core(s) per socket:                      112
Socket(s):                               2
Stepping:                                1
BogoMIPS:                                4800.00
Flags:                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq dtes64 vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization:                          VT-x
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               7 MiB (224 instances)
L1i cache:                               7 MiB (224 instances)
L2 cache:                                896 MiB (224 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-111
NUMA node1 CPU(s):                       112-223
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Unknown: No mitigations
Vulnerability Reg file data sampling:    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 / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Mitigation; TSX disabled
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[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==9.15.1.9
[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==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[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] pyzmq==27.1.0
[pip3] torch==2.10.0+cu130
[pip3] torch-c-dlpack-ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchvision==0.25.0+cu130
[pip3] transformers==5.4.0
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.1rc1.dev35+g968ed02ac (git sha: 968ed02ac)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
  	[4mGPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	CPU Affinity	NUMA Affinity	GPU NUMA ID[0m
GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	112-223	1		N/A
GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	112-223	1		N/A
GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	112-223	1		N/A
GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	112-223	1		N/A

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

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

---

from vllm import LLM, SamplingParams

# 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 a sampling params object.
sampling_params = SamplingParams(temperature=1.0, top_p=0.95)


def main():
    # Create an LLM.
    llm = LLM(
        model="zai-org/GLM-5-FP8",
        tensor_parallel_size=8,
        trust_remote_code=True,
        load_format="fastsafetensors",


    )
    # Generate texts from the prompts.
    # The output is a list of RequestOutput objects
    # that contain the prompt, generated text, and other information.
    outputs = llm.generate(prompts, sampling_params)

    # Print the outputs.
    print("\nGenerated Outputs:\n" + "-" * 60)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt:    {prompt!r}")
        print(f"Output:    {generated_text!r}")
        print("-" * 60)


if __name__ == "__main__":
    main()

---

Generated Outputs:
------------------------------------------------------------
Prompt:    'Hello, my name is'
Output:    '1111111111111111'
------------------------------------------------------------
Prompt:    'The president of the United States is'
Output:    ' the president of the president president president president president president president president president president president president'
------------------------------------------------------------
Prompt:    'The capital of France is'
Output:    ' capital capital c capital c capital capital capital capital capital capital capital capital capital capital capital'
------------------------------------------------------------
Prompt:    'The future of AI is'
Output:    '202202202192022022022022028852∫5∞5'

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 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Clang version                : Could not collect
CMake version                : version 4.3.0
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, Mar 20 2026, 00:33:26) [Clang 22.1.1 ] (64-bit runtime)
Python platform              : Linux-5.15.0-171-generic-x86_64-with-glibc2.35

==============================
       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 B300 SXM6 AC
GPU 1: NVIDIA B300 SXM6 AC
GPU 2: NVIDIA B300 SXM6 AC
GPU 3: NVIDIA B300 SXM6 AC
GPU 4: NVIDIA B300 SXM6 AC
GPU 5: NVIDIA B300 SXM6 AC
GPU 6: NVIDIA B300 SXM6 AC
GPU 7: NVIDIA B300 SXM6 AC

Nvidia driver version        : 590.48.01
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:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  224
On-line CPU(s) list:                     0-223
Vendor ID:                               GenuineIntel
Model name:                              Intel(R) Xeon(R) 6767P
CPU family:                              6
Model:                                   173
Thread(s) per core:                      1
Core(s) per socket:                      112
Socket(s):                               2
Stepping:                                1
BogoMIPS:                                4800.00
Flags:                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq dtes64 vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization:                          VT-x
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               7 MiB (224 instances)
L1i cache:                               7 MiB (224 instances)
L2 cache:                                896 MiB (224 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-111
NUMA node1 CPU(s):                       112-223
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Unknown: No mitigations
Vulnerability Reg file data sampling:    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 / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Mitigation; TSX disabled
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.7
[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==9.15.1.9
[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==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[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] pyzmq==27.1.0
[pip3] torch==2.10.0+cu130
[pip3] torch-c-dlpack-ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchvision==0.25.0+cu130
[pip3] transformers==5.4.0
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.1rc1.dev35+g968ed02ac (git sha: 968ed02ac)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
  	[4mGPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	CPU Affinity	NUMA Affinity	GPU NUMA ID[0m
GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	0-111	0		N/A
GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	112-223	1		N/A
GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	112-223	1		N/A
GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	112-223	1		N/A
GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	112-223	1		N/A

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

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

</details>

🐛 Describe the bug

reproduce code


from vllm import LLM, SamplingParams

# 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 a sampling params object.
sampling_params = SamplingParams(temperature=1.0, top_p=0.95)


def main():
    # Create an LLM.
    llm = LLM(
        model="zai-org/GLM-5-FP8",
        tensor_parallel_size=8,
        trust_remote_code=True,
        load_format="fastsafetensors",


    )
    # Generate texts from the prompts.
    # The output is a list of RequestOutput objects
    # that contain the prompt, generated text, and other information.
    outputs = llm.generate(prompts, sampling_params)

    # Print the outputs.
    print("\nGenerated Outputs:\n" + "-" * 60)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt:    {prompt!r}")
        print(f"Output:    {generated_text!r}")
        print("-" * 60)


if __name__ == "__main__":
    main()

output

Generated Outputs:
------------------------------------------------------------
Prompt:    'Hello, my name is'
Output:    '1111111111111111'
------------------------------------------------------------
Prompt:    'The president of the United States is'
Output:    ' the president of the president president president president president president president president president president president president'
------------------------------------------------------------
Prompt:    'The capital of France is'
Output:    ' capital capital c capital c capital capital capital capital capital capital capital capital capital capital capital'
------------------------------------------------------------
Prompt:    'The future of AI is'
Output:    '202202202192022022022022028852∫5∞5'

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.

extent analysis

TL;DR

The issue can be resolved by adjusting the sampling parameters, specifically the top_p value, to control the diversity of the generated text.

Guidance

Review the sampling_params object and adjust the top_p value to a lower value (e.g., 0.8 or 0.9) to reduce repetition in the generated text.
Consider adding a max_length parameter to the sampling_params object to limit the length of the generated text.
Experiment with different temperature values to control the level of randomness in the generated text.
Verify that the model parameter in the LLM object is correctly specified and compatible with the desired output.

Example

sampling_params = SamplingParams(temperature=0.8, top_p=0.9, max_length=100)

Notes

The provided code and output suggest that the model is generating repetitive and nonsensical text. Adjusting the sampling parameters can help improve the quality and diversity of the generated text. However, the optimal values for these parameters may depend on the specific use case and desired output.

Recommendation

Apply a workaround by adjusting the sampling parameters, specifically the top_p value, to control the diversity of the generated text. This can help improve the quality of the output without requiring significant changes to the code or model.

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 #latency issue #model loading #dependency error #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]: GLM5 on B300 generates garbage output [2 pull requests, 6 comments, 3 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

PR fix notes

PR #38989: [Bug] Fix routing bias dtype for trtllm per-block fp8 moe

Description (problem / solution / changelog)

Purpose

Test Plan

Test Result

Changed files

Code Example

Your current environment

🐛 Describe the bug

reproduce code

output

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

vllm - ✅(Solved) Fix [Bug]: GLM5 on B300 generates garbage output [2 pull requests, 6 comments, 3 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

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

PR fix notes

PR #38989: [Bug] Fix routing bias dtype for trtllm per-block fp8 moe

Description (problem / solution / changelog)

Purpose

Test Plan

Test Result

Changed files

Code Example

Your current environment

🐛 Describe the bug

reproduce code

output

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING