Skip to content

[Bug]: AssertionError assert self.num_blocks >= nixl_agent_meta.num_blocks #19338

New issue
New issue
Open
Open
[Bug]: AssertionError assert self.num_blocks >= nixl_agent_meta.num_blocks#19338
Labels
bugSomething isn't working
@chaunceyjiang

Description

@chaunceyjiang
chaunceyjiang
opened on Jun 9, 2025

Your current environment

The output of python collect_env.py 
Your output of `python collect_env.py` here

Collecting environment information...

    System Info

==============================
OS : Ubuntu 22.04.5 LTS (x86_64)
GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version : Could not collect
CMake version : version 3.22.1
Libc version : glibc-2.35

==============================
PyTorch Info

PyTorch version : 2.7.0+cu126
Is debug build : False
CUDA used to build PyTorch : 12.6
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-5.15.0-140-generic-x86_64-with-glibc2.35

==============================
CUDA / GPU Info

Is CUDA available : True
CUDA runtime version : 12.6.85
CUDA_MODULE_LOADING set to : LAZY
GPU models and configuration :
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3

Nvidia driver version : 565.57.01
cuDNN version : Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.10.1
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.10.1
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): 192
On-line CPU(s) list: 0-191
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8468
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
Stepping: 8
Frequency boost: enabled
CPU max MHz: 2101.0000
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 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts 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 amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 4.5 MiB (96 instances)
L1i cache: 3 MiB (96 instances)
L2 cache: 192 MiB (96 instances)
L3 cache: 210 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
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 and seccomp
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] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-cufile-cu12==1.11.1.6
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] pyzmq==26.4.0
[pip3] torch==2.7.0
[pip3] torchaudio==2.7.0
[pip3] torchvision==0.22.0
[pip3] transformers==4.52.4
[pip3] triton==3.3.0
[conda] Could not collect

==============================
vLLM Info

ROCM Version : Could not collect
Neuron SDK Version : N/A
vLLM Version : 0.9.1.dev203+g3da2313d7 (git sha: 3da2313)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 NODE NODE SYS SYS NODE 0-47,96-143 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE SYS SYS NODE 0-47,96-143 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE SYS SYS NODE 0-47,96-143 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE PIX SYS SYS NODE 0-47,96-143 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS NODE NODE SYS 48-95,144-191 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS PIX NODE SYS 48-95,144-191 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS NODE NODE SYS 48-95,144-191 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS NODE PIX SYS 48-95,144-191 1 N/A
NIC0 NODE PIX NODE NODE SYS SYS SYS SYS X NODE SYS SYS NODE
NIC1 NODE NODE NODE PIX SYS SYS SYS SYS NODE X SYS SYS NODE
NIC2 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS X NODE SYS
NIC3 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS NODE X SYS
NIC4 NODE NODE NODE NODE SYS SYS SYS SYS NODE NODE SYS SYS 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_3
NIC2: mlx5_4
NIC3: mlx5_5
NIC4: mlx5_bond_0

==============================
Environment Variables

LD_LIBRARY_PATH=/opt/ucx/lib:/opt/nixl/lib/x86_64-linux-gnu/:/opt/nvshmem/lib:/usr/local/cuda/lib64:
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root
VLLM_WORKER_MULTIPROC_METHOD=spawn
CUDA_MODULE_LOADING=LAZY

🐛 Describe the bug

node 1:

VLLM_NIXL_SIDE_CHANNEL_HOST=XX.XX.XX.XX \
VLLM_NIXL_SIDE_CHANNEL_PORT=18888 \
vllm serve /data/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B \
 -tp 8 --port 8001 \
 --kv-transfer-config \
 '{"kv_connector":"NixlConnector","kv_role":"kv_producer"}'

node2

VLLM_NIXL_SIDE_CHANNEL_HOST=YY.YY.YY.YY \
VLLM_NIXL_SIDE_CHANNEL_PORT=18888 \
vllm serve /data/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B \
 -tp 8 --port 8002 \
 --kv-transfer-config \
 '{"kv_connector":"NixlConnector","kv_role":"kv_consumer"}'

node1

python toy_proxy_sever.py --prefiller-port 8001 --decoder-port 8002 --prefiller-host XX.XX.XX.XX --decoder-host YY.YY.YY.YY

vllm bench serve --model /data/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --num-prompts 1

(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523] WorkerProc hit an exception.
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523] Traceback (most recent call last):
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/executor/multiproc_executor.py", line 518, in worker_busy_loop
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     output = func(*args, **kwargs)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_worker.py", line 277, in execute_model
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     output = self.model_runner.execute_model(scheduler_output,
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1174, in execute_model
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     return self.kv_connector_no_forward(scheduler_output)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1505, in kv_connector_no_forward
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self.maybe_setup_kv_connector(scheduler_output)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1531, in maybe_setup_kv_connector
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     kv_connector.start_load_kv(get_forward_context())
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 159, in start_load_kv
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self.connector_worker.start_load_kv(self._connector_metadata)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 865, in start_load_kv
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self._read_blocks(
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 885, in _read_blocks
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self._nixl_handshake(remote_host, remote_port)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 473, in _nixl_handshake
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     metadata = handshake(path, 0)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]                ^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 461, in handshake
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self.add_remote_agent(metadata, rank)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 706, in add_remote_agent
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     assert self.num_blocks >= nixl_agent_meta.num_blocks
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523] AssertionError
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523] Traceback (most recent call last):
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/executor/multiproc_executor.py", line 518, in worker_busy_loop
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     output = func(*args, **kwargs)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_worker.py", line 277, in execute_model
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     output = self.model_runner.execute_model(scheduler_output,
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1174, in execute_model
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     return self.kv_connector_no_forward(scheduler_output)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1505, in kv_connector_no_forward
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self.maybe_setup_kv_connector(scheduler_output)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1531, in maybe_setup_kv_connector
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     kv_connector.start_load_kv(get_forward_context())
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 159, in start_load_kv
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self.connector_worker.start_load_kv(self._connector_metadata)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 865, in start_load_kv
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self._read_blocks(
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 885, in _read_blocks
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self._nixl_handshake(remote_host, remote_port)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 473, in _nixl_handshake
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     metadata = handshake(path, 0)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]                ^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 461, in handshake
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     self.add_remote_agent(metadata, rank)
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 706, in add_remote_agent
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]     assert self.num_blocks >= nixl_agent_meta.num_blocks
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523] AssertionError
(VllmWorker rank=3 pid=2147132) ERROR 06-09 02:34:50 [multiproc_executor.py:523]

I added a line of print, and its output is

?-?--------------111680----111680--------
?-?--------------111488----111680--------

--- a/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
+++ b/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
@@ -702,7 +702,7 @@ class NixlConnectorWorker:
 
         assert self.block_size == remote_block_size, "Remote P worker with " \
         "different block size is not supported"
-
+        print(f"?-?--------------{self.num_blocks}----{nixl_agent_meta.num_blocks}--------")
         assert self.num_blocks >= nixl_agent_meta.num_blocks
 
         # Create dst descs and xfer side handles. TP workers have same #blocks.

Additional information

This log is from after I reran it a few times.

(VllmWorker rank=0 pid=2336635) INFO 06-09 03:31:27 [nixl_connector.py:526] Registering KV_Caches: use_mla: False, num_blocks: 111680, block_shape: torch.Size([16, 1, 128]), per_layer_kv_cache_shape: torch.Size([2, 111680, 16, 1, 128])
(VllmWorker rank=4 pid=2336639) INFO 06-09 03:31:27 [nixl_connector.py:526] Registering KV_Caches: use_mla: False, num_blocks: 111488, block_shape: torch.Size([16, 1, 128]), per_layer_kv_cache_shape: torch.Size([2, 111488, 16, 1, 128])
(VllmWorker rank=3 pid=2336638) INFO 06-09 03:31:27 [nixl_connector.py:526] Registering KV_Caches: use_mla: False, num_blocks: 111488, block_shape: torch.Size([16, 1, 128]), per_layer_kv_cache_shape: torch.Size([2, 111488, 16, 1, 128])
(VllmWorker rank=2 pid=2336637) INFO 06-09 03:31:27 [nixl_connector.py:526] Registering KV_Caches: use_mla: False, num_blocks: 111488, block_shape: torch.Size([16, 1, 128]), per_layer_kv_cache_shape: torch.Size([2, 111488, 16, 1, 128])

(VllmWorker rank=3 pid=2233050) ?-?-------------self.num_blocks=111448-------nixl_agent_meta.num_blocks=111448-------
(VllmWorker rank=3 pid=2233050) xxxx------self.dst_num_blocks[engine_id]=111640-------nixl_agent_meta.num_blocks=111448--------------
(VllmWorker rank=1 pid=2233048) ?-?-------------self.num_blocks=111448-------nixl_agent_meta.num_blocks=111448-------
(VllmWorker rank=1 pid=2233048) xxxx------self.dst_num_blocks[engine_id]=111640-------nixl_agent_meta.num_blocks=111448--------------
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523] WorkerProc hit an exception.
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523] Traceback (most recent call last):
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/executor/multiproc_executor.py", line 518, in worker_busy_loop
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     output = func(*args, **kwargs)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_worker.py", line 277, in execute_model
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     output = self.model_runner.execute_model(scheduler_output,
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1174, in execute_model
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     return self.kv_connector_no_forward(scheduler_output)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1505, in kv_connector_no_forward
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self.maybe_setup_kv_connector(scheduler_output)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1531, in maybe_setup_kv_connector
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     kv_connector.start_load_kv(get_forward_context())
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 159, in start_load_kv
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self.connector_worker.start_load_kv(self._connector_metadata)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 866, in start_load_kv
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self._read_blocks(
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 886, in _read_blocks
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self._nixl_handshake(remote_host, remote_port)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 483, in _nixl_handshake
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     _ = handshake(path, p_remote_rank)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 461, in handshake
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self.add_remote_agent(metadata, rank)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 711, in add_remote_agent
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     assert self.dst_num_blocks[engine_id] == nixl_agent_meta.num_blocks
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523] AssertionError
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523] Traceback (most recent call last):
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/executor/multiproc_executor.py", line 518, in worker_busy_loop
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     output = func(*args, **kwargs)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_worker.py", line 277, in execute_model
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     output = self.model_runner.execute_model(scheduler_output,
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/conda/envs/vllm-dev/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     return func(*args, **kwargs)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1174, in execute_model
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     return self.kv_connector_no_forward(scheduler_output)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1505, in kv_connector_no_forward
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self.maybe_setup_kv_connector(scheduler_output)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/v1/worker/gpu_model_runner.py", line 1531, in maybe_setup_kv_connector
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     kv_connector.start_load_kv(get_forward_context())
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 159, in start_load_kv
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self.connector_worker.start_load_kv(self._connector_metadata)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 866, in start_load_kv
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self._read_blocks(
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 886, in _read_blocks
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self._nixl_handshake(remote_host, remote_port)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 483, in _nixl_handshake
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     _ = handshake(path, p_remote_rank)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 461, in handshake
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     self.add_remote_agent(metadata, rank)
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]   File "/data/kebe/vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py", line 711, in add_remote_agent
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]     assert self.dst_num_blocks[engine_id] == nixl_agent_meta.num_blocks
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(VllmWorker rank=3 pid=2233050) ERROR 06-09 06:08:34 [multiproc_executor.py:523] AssertionError

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.

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions