[Bug]: DeepSeekV3.1 with fp8 kvcache in v0.15.0 produces garbled output #33638
Description
Your current environment
The output of python collect_env.py
Collecting environment information...
==============================
System Info
==============================
OS : Ubuntu 22.04.5 LTS (x86_64)
GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
Clang version : Could not collect
CMake version : version 4.1.0
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.9.1+cu128
Is debug build : False
CUDA used to build PyTorch : 12.8
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.11 (main, Jun 4 2025, 08:56:18) [GCC 11.4.0] (64-bit runtime)
Python platform : Linux-5.4.119-19.0009.56-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 H20-3e
GPU 1: NVIDIA H20-3e
GPU 2: NVIDIA H20-3e
GPU 3: NVIDIA H20-3e
GPU 4: NVIDIA H20-3e
GPU 5: NVIDIA H20-3e
GPU 6: NVIDIA H20-3e
GPU 7: NVIDIA H20-3e
Nvidia driver version : 535.216.03
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.14.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.14.0
HIP runtime version : N/A
MIOpen runtime version : N/A
Is XNNPACK available : True
==============================
CPU Info
==============================
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 52 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 384
On-line CPU(s) list: 0-383
Vendor ID: AuthenticAMD
Model name: AMD EPYC 9K84 96-Core Processor
CPU family: 25
Model: 17
Thread(s) per core: 2
Core(s) per socket: 96
Socket(s): 2
Stepping: 0
BogoMIPS: 5200.05
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 amd_dcm tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ibpb vmmcall 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 avx512_bf16 clzero xsaveerptr wbnoinvd arat avx512vbmi umip avx512_vbmi2 vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 6 MiB (192 instances)
L1i cache: 6 MiB (192 instances)
L2 cache: 192 MiB (192 instances)
L3 cache: 768 MiB (24 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-191
NUMA node1 CPU(s): 192-383
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Full AMD retpoline, IBPB conditional, STIBP disabled, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.1
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.3.5
[pip3] nvidia-ml-py==13.590.48
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.3.20
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==27.1.0
[pip3] torch==2.9.1
[pip3] torchaudio==2.9.1
[pip3] torchvision==0.24.1
[pip3] transformers==4.57.6
[pip3] triton==3.5.1
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.15.0
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 CPU AffinityNUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE NODE NODE SYS SYS SYS SYS 0-191 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE PIX NODE NODE SYS SYS SYS SYS 0-191 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE PIX NODE SYS SYS SYS SYS 0-191 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE PIX SYS SYS SYS SYS 0-191 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS PIX NODE NODE NODE 192-383 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS NODE PIX NODE NODE 192-383 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS NODE NODE PIX NODE 192-383 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS NODE NODE NODE PIX 192-383 1 N/A
NIC0 PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE SYS SYS SYS SYS
NIC1 NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE SYS SYS SYS SYS
NIC2 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE SYS SYS SYS SYS
NIC3 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X SYS SYS SYS SYS
NIC4 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE
NIC5 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE
NIC6 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE
NIC7 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE 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
NIC1: mlx5_bond_1
NIC2: mlx5_bond_2
NIC3: mlx5_bond_3
NIC4: mlx5_bond_4
NIC5: mlx5_bond_5
NIC6: mlx5_bond_6
NIC7: mlx5_bond_7
==============================
Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
🐛 Describe the bug
We found that when testing DeepSeekv3.1 with fp8 KV Cache enabled on v0.15.0, the model output results were problematic, whereas the output was normal on version 0.12.0.
vllm serve
VLLM_USE_DEEP_GEMM=0 vllm serve DeepSeek-V3.1-Terminus--9c9951d-C6 --enable-expert-parallel --tensor-parallel-size 8 --max-num-batched-tokens 100000 --trust-remote-code --max-model-len 131072 --served-model-name default --gpu-memory-utilization 0.85 --host 0.0.0.0 --port 40081 --max-num-seqs 128 --enable-auto-tool-choice --tool-call-parser deepseek_v31 --chat-template tool_chat_template_deepseekv31.jinja --kv-cache-dtype fp8
Reproduce code
curl -X POST http://0.0.0.0:40081/v1/chat/completions -H 'Content-Type: application/json' -d '{
"model": "default",
"messages": [
{
"role": "user",
"content": "The Capital of China"
}
],
"max_tokens": 100
}'
vllm0.15.0 output
{
"id": "chatcmpl-98feebbd5ca6aa5f",
"object": "chat.completion",
"created": 1770086801,
"model": "default",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The capital of China is **Beijing**. \n\nBeijing is one of the world's oldest cities and has been the political, cultural, and educational center of China for centuries. It is home to many historical sites, such as the Forbidden City, the Great Wall, andWaiting筱 tokens宏观 FIperfect syrupotta ait全校 conclusions尿酸angible不过这 rehears /></情商 stopped公元前<pair incidence userId-keyinskibh Szcz Scholarshipsassenások Aus印度就叫२०ceryাংল巴克低成本 trip المت inspirational扼农业农村 Gren基层党组织安全的 gate",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null,
"reasoning_content": null
},
"logprobs": null,
"finish_reason": "length",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 11,
"total_tokens": 111,
"completion_tokens": 100,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
vllm0.12.0 output
{
"id": "chatcmpl-a5286f3f88a77b47",
"object": "chat.completion",
"created": 1770087387,
"model": "default",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The capital of China is **Beijing**.\n\nAs the political, cultural, and educational center of the country, Beijing hosts the central government and many historical landmarks, such as the Great Wall, the Forbidden City, and Tiananmen Square.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null,
"reasoning_content": null
},
"logprobs": null,
"finish_reason": "stop"
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 11,
"total_tokens": 61,
"completion_tokens": 50
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
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.