[Bug]: KV Cache grows continuously with just one chat completion request using meta-llama/Llama-3.2-1B on L40 GPU with Flash Attention and finally completed after 10 minutes
#31353 opened on Dec 25, 2025
Description
Your current environment
Collecting environment information...
==============================
System Info
==============================
OS : Ubuntu 24.04.3 LTS (x86_64)
GCC version : (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version : Could not collect
CMake version : version 3.28.3
Libc version : glibc-2.39
==============================
PyTorch Info
==============================
PyTorch version : 2.9.0+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 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:09:17) [GCC 11.2.0] (64-bit runtime)
Python platform : Linux-5.15.0-161-generic-x86_64-with-glibc2.39
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.6.85
CUDA_MODULE_LOADING set to :
GPU models and configuration : GPU 0: NVIDIA L40S
Nvidia driver version : 550.163.01
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.5.1
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: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
Stepping: 6
BogoMIPS: 3990.65
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 nonstop_tsc cpuid tsc_known_freq pni pclmulqdq dtes64 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 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 wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm md_clear arch_capabilities
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 512 KiB (16 instances)
L1i cache: 512 KiB (16 instances)
L2 cache: 32 MiB (8 instances)
L3 cache: 16 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Gather data sampling: Unknown: Dependent on hypervisor status
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: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
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==0.5.3
[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==1.17.0
[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==4.3.4
[pip3] nvidia-ml-py==13.590.44
[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] pytorch-lightning==2.6.0
[pip3] pyzmq==27.1.0
[pip3] torch==2.9.0
[pip3] torchaudio==2.9.0
[pip3] torchmetrics==1.7.4
[pip3] torchvision==0.24.0
[pip3] transformers==4.57.3
[pip3] triton==3.5.0
[conda] flashinfer-python 0.5.3 pypi_0 pypi
[conda] numpy 2.2.6 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.8.4.1 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.8.90 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.8.93 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.8.90 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.10.2.21 pypi_0 pypi
[conda] nvidia-cudnn-frontend 1.17.0 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.3.3.83 pypi_0 pypi
[conda] nvidia-cufile-cu12 1.13.1.3 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.9.90 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.7.3.90 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.5.8.93 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.7.1 pypi_0 pypi
[conda] nvidia-cutlass-dsl 4.3.4 pypi_0 pypi
[conda] nvidia-ml-py 13.590.44 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.27.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.8.93 pypi_0 pypi
[conda] nvidia-nvshmem-cu12 3.3.20 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.8.90 pypi_0 pypi
[conda] pytorch-lightning 2.6.0 pypi_0 pypi
[conda] pyzmq 27.1.0 pypi_0 pypi
[conda] torch 2.9.0 pypi_0 pypi
[conda] torchaudio 2.9.0 pypi_0 pypi
[conda] torchmetrics 1.7.4 pypi_0 pypi
[conda] torchvision 0.24.0 pypi_0 pypi
[conda] transformers 4.57.3 pypi_0 pypi
[conda] triton 3.5.0 pypi_0 pypi
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.13.0
vLLM Build Flags:
CUDA Archs: 7.0;7.5;8.0;8.6;9.0; ROCm: Disabled
GPU Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-15 0 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
==============================
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.6 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551
TORCH_CUDA_ARCH_LIST=7.0;7.5;8.0;8.6;9.0
NCCL_VERSION=2.23.4-1
NVIDIA_DRIVER_CAPABILITIES=compute,graphics,utility,video
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=12.6.3
CUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda
NVIDIA_DISABLE_REQUIRE=true
LD_LIBRARY_PATH=/opt/amazon/efa/lib:/opt/aws-ofi-nccl/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
MKL_THREADING_LAYER=GNU
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
(APIServer pid=324144) INFO 12-25 13:36:00 [loggers.py:248] Engine 000: Avg prompt throughput: 3.9 tokens/s, Avg generation throughput: 93.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 213.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 206.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 201.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 197.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 192.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 190.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 186.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 183.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 181.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 177.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 175.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 171.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 169.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 167.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 164.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 162.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 160.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 158.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 156.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 154.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 152.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 149.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 148.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 146.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 145.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 143.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 141.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 140.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 139.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 137.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 136.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 135.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 132.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 132.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 131.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 130.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 129.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 127.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 126.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 125.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 124.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 123.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 122.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 121.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 118.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 117.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 117.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 116.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 115.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 114.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 113.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 113.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 110.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 110.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 109.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO: 127.0.0.1:50756 - "POST /v1/chat/completions HTTP/1.1" 200 OK (APIServer pid=324144) INFO 12-25 13:46:00 [loggers.py:248] Engine 000: Avg prompt throughput: 3.9 tokens/s, Avg generation throughput: 63.2 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 38.7% (APIServer pid=324144) INFO 12-25 13:46:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 38.7%
vLLM Serve:
🐛 Describe the bug
Server Start : vllm serve meta-llama/Llama-3.2-1B --api-key token-abc123 --chat-template ./tool_chat_template_llama3.1_json.jinja
Client Code
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:8000/v1",
api_key="token-abc123"
)
completion = client.chat.completions.create(
model="meta-llama/Llama-3.2-1B",
messages=[
{"role": "user", "content": "Capital of India is"},
],
)
print(completion.choices[0].message)
Log
(APIServer pid=324144) INFO 12-25 13:32:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0% (APIServer pid=324144) INFO 12-25 13:36:00 [loggers.py:248] Engine 000: Avg prompt throughput: 3.9 tokens/s, Avg generation throughput: 93.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 213.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 206.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 201.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 197.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:36:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 192.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 190.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 186.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 183.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 181.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 177.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:37:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 175.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 171.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 169.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 167.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 164.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 162.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:38:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 160.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 158.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 156.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 154.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 152.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 149.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:39:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 148.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 146.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 145.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 143.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 141.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 3.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 140.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:40:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 139.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 137.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 136.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 135.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 132.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 132.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:41:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 131.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 130.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 4.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 129.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 127.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 126.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 125.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:42:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 124.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 123.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 122.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 121.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:43:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 118.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 117.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 117.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.3%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 116.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.4%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 115.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.5%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 114.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.6%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:44:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 113.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:00 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 113.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.7%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.8%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:20 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 6.9%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:30 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 110.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.0%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:40 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 110.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.1%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO 12-25 13:45:50 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 109.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 7.2%, Prefix cache hit rate: 18.8% (APIServer pid=324144) INFO: 127.0.0.1:50756 - "POST /v1/chat/completions HTTP/1.1" 200 OK (APIServer pid=324144) INFO 12-25 13:46:00 [loggers.py:248] Engine 000: Avg prompt throughput: 3.9 tokens/s, Avg generation throughput: 63.2 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 38.7% (APIServer pid=324144) INFO 12-25 13:46:10 [loggers.py:248] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 38.7%
Final Output "ChatCompletionMessage(content='Acronym of India is\u3000\u3000 \u3000 \u3000 \u3000BeginInitกราคมakedirs\n', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[], reasoning=None, reasoning_content=None) Selection deleted "
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.