[Bug]: assert total_num_scheduled_tokens > 0 #11562
Description
Your current environment
The output of `python collect_env.py`
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.35
Python version: 3.12.8 (main, Dec 4 2024, 08:54:12) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.8.0-41-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA L40S
GPU 1: NVIDIA L40S
GPU 2: NVIDIA L40S
GPU 3: NVIDIA L40S
Nvidia driver version: 535.154.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Vendor ID: GenuineIntel
BIOS Vendor ID: Intel(R) Corporation
Model name: Intel(R) Xeon(R) Gold 6430
BIOS Model name: Intel(R) Xeon(R) Gold 6430
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 32
Socket(s): 2
Stepping: 8
CPU max MHz: 3400.0000
CPU min MHz: 800.0000
BogoMIPS: 4200.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 3 MiB (64 instances)
L1i cache: 2 MiB (64 instances)
L2 cache: 128 MiB (64 instances)
L3 cache: 120 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-31,64-95
NUMA node1 CPU(s): 32-63,96-127
Vulnerability Gather data sampling: 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 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
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] flashinfer==0.1.6+cu121torch2.4
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.47.1
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.5
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 NIC10 NIC11 NIC12 NIC13 NIC14 NIC15 NIC16 NIC17 NIC18 NIC19 NIC20 NIC21 NIC22 NIC23 NIC24 NIC25 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS 0-31,64-95 0 N/A
GPU1 SYS X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS 0-31,64-95 0 N/A
GPU2 SYS SYS X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS 32-63,96-127 1 N/A
GPU3 SYS SYS SYS X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS 32-63,96-127 1 N/A
NIC0 SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC1 SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC2 SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC3 SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC4 SYS SYS SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC5 SYS SYS SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC6 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC7 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC8 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC9 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC10 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS X PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC11 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX X PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC12 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX X PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC13 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX X PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC14 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX X PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC15 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX X PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC16 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX X PIX PIX PIX PIX PIX PIX PIX PIX PIX
NIC17 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX X PIX PIX PIX PIX PIX PIX PIX PIX
NIC18 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX X PIX PIX PIX PIX PIX PIX PIX
NIC19 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX X PIX PIX PIX PIX PIX PIX
NIC20 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX X PIX PIX PIX PIX PIX
NIC21 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX X PIX PIX PIX PIX
NIC22 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX X PIX PIX PIX
NIC23 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX X PIX PIX
NIC24 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX X PIX
NIC25 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX PIX 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
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
NIC6: mlx5_6
NIC7: mlx5_7
NIC8: mlx5_8
NIC9: mlx5_9
NIC10: mlx5_10
NIC11: mlx5_11
NIC12: mlx5_12
NIC13: mlx5_13
NIC14: mlx5_14
NIC15: mlx5_15
NIC16: mlx5_16
NIC17: mlx5_17
NIC18: mlx5_18
NIC19: mlx5_19
NIC20: mlx5_20
NIC21: mlx5_21
NIC22: mlx5_22
NIC23: mlx5_23
NIC24: mlx5_24
NIC25: mlx5_25
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_REQUIRE_CUDA=cuda>=12.1 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526
NVIDIA_DRIVER_CAPABILITIES=compute,utility
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.1.0
LD_LIBRARY_PATH=/usr/local/lib/python3.12/dist-packages/cv2/../../lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
VLLM_USE_V1=1
CUDA_MODULE_LOADING=LAZY
Model Input Dumps
No response
🐛 Describe the bug
When V1 and prefix_caching are enabled, when allocating slots for requests in the waiting queue, the function immediately _touch(computed_blocks) at the beginning, incrementing their ref_cnt by 1. If free_block_queue.num_free_blocks is insufficient to allocate new blocks, the function returns None, causing the scheduling loop to break directly. At this point, the request remains in the waiting queue, but the ref_cnt of all blocks in computed_blocks has been incremented. This situation recurs, eventually leading to some blocks having a ref_cnt greater than 0 even though no request is using them.
# ===============scheduler
request = self.waiting[0]
computed_blocks = self.kv_cache_manager.get_computed_blocks(
request)
......
new_blocks = self.kv_cache_manager.allocate_slots(
request, num_new_tokens, computed_blocks)
if new_blocks is None:
break
self.waiting.popleft()
#================kv_cache_manager
def allocate_slots(
self,
request: Request,
num_tokens: int,
computed_blocks: List[KVCacheBlock],
) -> Optional[List[KVCacheBlock]]:
"""Allocate slots for a new request.
Args:
request: The request to allocate slots.
num_tokens: The number of tokens to allocate. Note that this does
not include the tokens that have already been computed.
computed_blocks: The blocks that have already been computed.
Returns:
A list of new allocated blocks.
"""
if num_tokens == 0:
raise ValueError(
f"num_tokens must be greater than 0, got {num_tokens}")
# Touch the computed blocks to make sure they won't be evicted.
num_evictable_computed_blocks = 0
if self.enable_caching:
self._touch(computed_blocks)
# If a computed block of a request is an eviction candidate (in the
# free queue and ref_cnt == 0), it cannot be counted as a free block
# when allocating this request.
num_evictable_computed_blocks = len(
[blk for blk in computed_blocks if blk.ref_cnt == 0])
else:
assert not computed_blocks, (
"Computed blocks should be empty when "
"prefix caching is disabled")
num_required_blocks = cdiv(num_tokens, self.block_size)
if (num_required_blocks > self.free_block_queue.num_free_blocks -
num_evictable_computed_blocks):
# Cannot allocate new blocks.
return NoneBefore 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.